Artifacts

{
  "mappings": [
    {
      "confidence": 0.95,
      "mappingType": "direct",
      "sourceField": "name",
      "justification": "Direct semantic match - both represent the primary name of the mineral occurrence",
      "targetAttribute": "name"
    },
    {
      "transform": {
        "type": "expression",
        "expression": "array_construct(minename) WHERE minename IS NOT NULL"
      },
      "confidence": 0.7,
      "mappingType": "inferred",
      "sourceField": "minename",
      "justification": "Mine name could serve as an alternative name for the occurrence, though it's a different entity type",
      "targetAttribute": "alternate_names"
    },
    {
      "transform": {
        "type": "lookup",
        "lookupTable": "occurrence_type_to_status"
      },
      "confidence": 0.6,
      "mappingType": "lookup",
      "sourceField": "mineraloccurrencetype",
      "justification": "Occurrence type (e.g., 'mineralized zone') may indicate operational status but needs value mapping to standard status terms",
      "targetAttribute": "status"
    },
    {
      "confidence": 0.9,
      "mappingType": "direct",
      "sourceField": "commodity",
      "justification": "Direct match - commodity field contains the primary mineral commodity (Gold, Iron, etc.)",
      "targetAttribute": "primary_commodity"
    },
    {
      "transform": {
        "type": "expression",
        "expression": "array_construct(map_commodity_to_symbol(commodity)) WHERE commodity IS NOT NULL"
      },
      "confidence": 0.8,
      "mappingType": "computed",
      "sourceField": "commodity",
      "justification": "Single commodity value needs to be converted to array format and potentially mapped to element symbols",
      "targetAttribute": "commodities"
    },
    {
      "confidence": 0.85,
      "mappingType": "direct",
      "sourceField": "mineraldepositmodel",
      "justification": "Mineral deposit model directly corresponds to geological classification of the deposit",
      "targetAttribute": "deposit_type"
    },
    {
      "confidence": 0.8,
      "mappingType": "direct",
      "sourceField": "hostgeologicunit",
      "justification": "Host geological unit name represents the primary host rock lithology",
      "targetAttribute": "host_rock"
    },
    {
      "confidence": 0.85,
      "mappingType": "direct",
      "sourceField": "geologichistory",
      "justification": "Geological history field contains age information like 'Paleoproterozoic'",
      "targetAttribute": "geological_age"
    },
    {
      "confidence": 0.95,
      "mappingType": "direct",
      "sourceField": "_id",
      "justification": "Primary identifier from the source dataset serves as the original source identifier",
      "targetAttribute": "source_id"
    }
  ],
  "featureType": "mineral_occurrence",
  "unmappedFields": [
    "_geom",
    "_featuretype",
    "hostgeologicunit_uri",
    "identifier",
    "mine_uri",
    "mineraloccurrenceshape",
    "mineraloccurrencetype_uri",
    "observationmethod",
    "positionalaccuracy",
    "representativeage_uri",
    "representativecommodity_uri",
    "representativeolderage_uri",
    "representativeyoungerage_uri",
    "source",
    "specification_uri",
    "_mirrored_at",
    "geom"
  ],
  "overallConfidence": 0.75,
  "suggestedAttributes": [
    {
      "name": "geometry",
      "dataType": "GEOMETRY",
      "description": "Point geometry representing the location of the mineral occurrence"
    },
    {
      "name": "external_identifier",
      "dataType": "TEXT",
      "description": "Persistent URI identifier from the original data source"
    },
    {
      "name": "positional_accuracy",
      "dataType": "TEXT",
      "description": "Description of location accuracy and positioning method"
    },
    {
      "name": "occurrence_shape",
      "dataType": "ENUM",
      "description": "Geometric shape classification of the mineral occurrence"
    },
    {
      "name": "last_updated",
      "dataType": "TIMESTAMP",
      "description": "Timestamp when the record was last synchronized or updated"
    }
  ]
}

{
  "isValid": true,
  "warnings": [
    "occurrence_type: Found 1 unexpected enum values: project",
    "geometry: 100% of values don't match expected type GEOMETRY"
  ],
  "sourceSlug": "au_ga_ozmin",
  "featureType": "mineral_occurrence",
  "suggestions": [],
  "validatedAt": "2026-02-09T21:50:02.995Z",
  "criticalIssues": [],
  "totalAttributes": 16,
  "validAttributes": 14,
  "validationScore": 88,
  "fieldValidations": [
    {
      "issues": [],
      "isValid": true,
      "nullCount": 0,
      "actualTypes": {
        "string": 16727
      },
      "nullPercent": 0,
      "expectedType": "TEXT",
      "matchedField": "name",
      "totalRecords": 16727,
      "attributeName": "name",
      "distinctCount": 12453,
      "sourcePatterns": [
        "name"
      ],
      "typeMismatchPercent": 0
    },
    {
      "issues": [
        "Found 1 unexpected enum values: project"
      ],
      "isValid": false,
      "nullCount": 0,
      "actualEnums": [
        "deposit",
        "mineralized zone",
        "project"
      ],
      "actualTypes": {
        "string": 16727
      },
      "nullPercent": 0,
      "expectedType": "TEXT",
      "matchedField": "mineraloccurrencetype",
      "missingEnums": [
        "prospect",
        "mine",
        "occurrence"
      ],
      "totalRecords": 16727,
      "attributeName": "occurrence_type",
      "distinctCount": 3,
      "expectedEnums": [
        "deposit",
        "mineralized zone",
        "prospect",
        "mine",
        "occurrence"
      ],
      "sourcePatterns": [
        "mineraloccurrencetype",
        "occurrence_type",
        "deposit_type"
      ],
      "unexpectedValues": [
        "project"
      ],
      "typeMismatchPercent": 0
    },
    {
      "issues": [],
      "isValid": true,
      "nullCount": 4136,
      "actualTypes": {
        "string": 12591
      },
      "nullPercent": 25,
      "expectedType": "TEXT",
      "matchedField": "commodity",
      "totalRecords": 16727,
      "attributeName": "commodity",
      "distinctCount": 1617,
      "sourcePatterns": [
        "commodity",
        "commodities",
        "mineral"
      ],
      "typeMismatchPercent": 0
    },
    {
      "issues": [],
      "isValid": true,
      "nullCount": 14804,
      "actualTypes": {
        "string": 1923
      },
      "nullPercent": 89,
      "expectedType": "TEXT",
      "matchedField": "mineraldepositmodel",
      "totalRecords": 16727,
      "attributeName": "deposit_model",
      "distinctCount": 119,
      "sourcePatterns": [
        "mineraldepositmodel",
        "deposit_model",
        "deposit_type"
      ],
      "typeMismatchPercent": 0
    },
    {
      "issues": [],
      "isValid": true,
      "nullCount": 13361,
      "actualTypes": {
        "string": 3366
      },
      "nullPercent": 80,
      "expectedType": "TEXT",
      "matchedField": "geologichistory",
      "totalRecords": 16727,
      "attributeName": "geological_age",
      "distinctCount": 8,
      "sourcePatterns": [
        "geologichistory",
        "geological_age",
        "age"
      ],
      "typeMismatchPercent": 0
    },
    {
      "issues": [],
      "isValid": true,
      "nullCount": 15342,
      "actualTypes": {
        "string": 1385
      },
      "nullPercent": 92,
      "expectedType": "TEXT",
      "matchedField": "hostgeologicunit",
      "totalRecords": 16727,
      "attributeName": "host_rock",
      "distinctCount": 837,
      "sourcePatterns": [
        "hostgeologicunit",
        "host_rock",
        "lithology"
      ],
      "typeMismatchPercent": 0
    },
    {
      "issues": [],
      "isValid": true,
      "nullCount": 14425,
      "actualTypes": {
        "string": 2302
      },
      "nullPercent": 86,
      "expectedType": "TEXT",
      "matchedField": "minename",
      "totalRecords": 16727,
      "attributeName": "mine_name",
      "distinctCount": 2237,
      "sourcePatterns": [
        "minename",
        "mine_name"
      ],
      "typeMismatchPercent": 0
    },
    {
      "issues": [],
      "isValid": true,
      "nullCount": 5583,
      "actualTypes": {
        "string": 11144
      },
      "nullPercent": 33,
      "expectedType": "TEXT",
      "matchedField": "positionalaccuracy",
      "totalRecords": 16727,
      "attributeName": "positional_accuracy",
      "distinctCount": 15,
      "sourcePatterns": [
        "positionalaccuracy",
        "accuracy",
        "location_method"
      ],
      "typeMismatchPercent": 0
    },
    {
      "issues": [],
      "isValid": true,
      "nullCount": 0,
      "actualTypes": {
        "string": 16727
      },
      "nullPercent": 0,
      "expectedType": "TEXT",
      "matchedField": "source",
      "totalRecords": 16727,
      "attributeName": "source_distance",
      "distinctCount": 46,
      "sourcePatterns": [
        "source"
      ],
      "typeMismatchPercent": 0
    },
    {
      "issues": [],
      "isValid": true,
      "nullCount": 15397,
      "actualTypes": {
        "string": 1330
      },
      "nullPercent": 92,
      "expectedType": "TEXT",
      "matchedField": "mineraloccurrenceshape",
      "totalRecords": 16727,
      "attributeName": "occurrence_shape",
      "distinctCount": 25,
      "sourcePatterns": [
        "mineraloccurrenceshape",
        "shape",
        "geometry_description"
      ],
      "typeMismatchPercent": 0
    },
    {
      "issues": [],
      "isValid": true,
      "nullCount": 0,
      "actualTypes": {
        "string": 16727
      },
      "nullPercent": 0,
      "expectedType": "TEXT",
      "matchedField": "observationmethod",
      "totalRecords": 16727,
      "attributeName": "observation_method",
      "distinctCount": 3,
      "sourcePatterns": [
        "observationmethod",
        "method",
        "classification_method"
      ],
      "typeMismatchPercent": 0
    },
    {
      "issues": [],
      "isValid": true,
      "nullCount": 0,
      "actualTypes": {
        "string": 16727
      },
      "nullPercent": 0,
      "expectedType": "TEXT",
      "matchedField": "identifier",
      "totalRecords": 16727,
      "attributeName": "source_id",
      "distinctCount": 16727,
      "sourcePatterns": [
        "identifier",
        "id",
        "source_id",
        "_id"
      ],
      "typeMismatchPercent": 0
    },
    {
      "issues": [],
      "isValid": true,
      "nullCount": 0,
      "actualTypes": {
        "string": 16727
      },
      "nullPercent": 0,
      "expectedType": "TEXT",
      "matchedField": "specification_uri",
      "totalRecords": 16727,
      "attributeName": "specification_uri",
      "distinctCount": 16727,
      "sourcePatterns": [
        "specification_uri",
        "uri",
        "reference_uri"
      ],
      "typeMismatchPercent": 0
    },
    {
      "issues": [],
      "isValid": true,
      "nullCount": 4165,
      "actualTypes": {
        "string": 12562
      },
      "nullPercent": 25,
      "expectedType": "TEXT",
      "matchedField": "representativecommodity_uri",
      "totalRecords": 16727,
      "attributeName": "commodity_uri",
      "distinctCount": 104,
      "sourcePatterns": [
        "representativecommodity_uri",
        "commodity_uri"
      ],
      "typeMismatchPercent": 0
    },
    {
      "issues": [],
      "isValid": true,
      "nullCount": 13361,
      "actualTypes": {
        "string": 3366
      },
      "nullPercent": 80,
      "expectedType": "TEXT",
      "matchedField": "representativeage_uri",
      "totalRecords": 16727,
      "attributeName": "age_uri",
      "distinctCount": 8,
      "sourcePatterns": [
        "representativeage_uri",
        "age_uri"
      ],
      "typeMismatchPercent": 0
    },
    {
      "issues": [
        "100% of values don't match expected type GEOMETRY"
      ],
      "isValid": false,
      "nullCount": 0,
      "actualTypes": {
        "string": 16727
      },
      "nullPercent": 0,
      "expectedType": "GEOMETRY",
      "matchedField": "_geom",
      "sampleIssues": [
        "POINT(143.387 -19.7352)",
        "POINT(128.8645 -19.587)",
        "POINT(140.5793 -32.0955)",
        "POINT(149.5208 -25.5081)",
        "POINT(120.9528 -30.312)"
      ],
      "totalRecords": 16727,
      "attributeName": "geometry",
      "distinctCount": 9557,
      "sourcePatterns": [
        "_geom",
        "geom",
        "geometry",
        "location"
      ],
      "typeMismatchPercent": 100
    }
  ],
  "recordsValidated": 16727,
  "attributesWithIssues": 2
}

{
  "domain": "mining",
  "qualityNotes": [
    "Many fields have null values, particularly commodity, geological history, and host rock information",
    "Positional accuracy varies and is often described as 'method unknown'",
    "The 'source' field appears to contain distance/scale information rather than data source",
    "Some records have coordinates that appear to be outside Australia (e.g., Point(21.7173 45.059))",
    "URI fields provide good linkage to controlled vocabularies but many are null",
    "Mine name field is consistently null across samples",
    "Duplicate geometry fields (_geom and geom) suggest data processing artifacts"
  ],
  "commonPatterns": {
    "dateFields": [
      "_mirrored_at"
    ],
    "statusFields": [
      "mineraloccurrencetype"
    ],
    "geometryFields": [
      "_geom",
      "geom"
    ],
    "commodityFields": [
      "commodity",
      "representativecommodity_uri"
    ],
    "identifierFields": [
      "_id",
      "identifier",
      "specification_uri"
    ],
    "measurementFields": [
      "source"
    ]
  },
  "alternativeTypes": [],
  "primaryFeatureType": {
    "name": "Mineral Occurrence",
    "slug": "mineral_occurrence",
    "reasoning": "This data clearly represents mineral occurrences based on the 'mineraloccurrencetype' field with values like 'mineralized zone' and 'deposit', the presence of commodity information, and the point geometry representing specific locations where minerals have been found.",
    "attributes": [
      {
        "name": "name",
        "dataType": "TEXT",
        "examples": [
          "Saddleback (Tunnel Road) (Boddington)",
          "Orativa",
          "Countess - underground"
        ],
        "required": true,
        "isGeometry": false,
        "description": "Name of the mineral occurrence",
        "isIdentifier": false,
        "sourceFieldPatterns": [
          "name"
        ]
      },
      {
        "name": "occurrence_type",
        "dataType": "TEXT",
        "examples": [
          "mineralized zone",
          "deposit"
        ],
        "required": false,
        "enumValues": [
          "deposit",
          "mineralized zone",
          "prospect",
          "mine",
          "occurrence"
        ],
        "isGeometry": false,
        "description": "Type of mineral occurrence (deposit, mineralized zone, prospect, etc.)",
        "isIdentifier": false,
        "sourceFieldPatterns": [
          "mineraloccurrencetype",
          "occurrence_type",
          "deposit_type"
        ]
      },
      {
        "name": "commodity",
        "dataType": "TEXT",
        "examples": [
          "Copper",
          "Gold",
          "Antimony, Gold"
        ],
        "required": false,
        "isGeometry": false,
        "description": "Primary commodity or mineral of interest",
        "isIdentifier": false,
        "sourceFieldPatterns": [
          "commodity",
          "commodities",
          "mineral"
        ]
      },
      {
        "name": "deposit_model",
        "dataType": "TEXT",
        "examples": [
          "Skarn gold ± copper ± tungsten"
        ],
        "required": false,
        "isGeometry": false,
        "description": "Geological model or type of mineral deposit",
        "isIdentifier": false,
        "sourceFieldPatterns": [
          "mineraldepositmodel",
          "deposit_model",
          "deposit_type"
        ]
      },
      {
        "name": "geological_age",
        "dataType": "TEXT",
        "examples": [
          "Archean"
        ],
        "required": false,
        "isGeometry": false,
        "description": "Geological age of the occurrence or host rock",
        "isIdentifier": false,
        "sourceFieldPatterns": [
          "geologichistory",
          "geological_age",
          "age"
        ]
      },
      {
        "name": "host_rock",
        "dataType": "TEXT",
        "required": false,
        "isGeometry": false,
        "description": "Host geological unit or rock type",
        "isIdentifier": false,
        "sourceFieldPatterns": [
          "hostgeologicunit",
          "host_rock",
          "lithology"
        ]
      },
      {
        "name": "mine_name",
        "dataType": "TEXT",
        "required": false,
        "isGeometry": false,
        "description": "Associated mine name if applicable",
        "isIdentifier": false,
        "sourceFieldPatterns": [
          "minename",
          "mine_name"
        ]
      },
      {
        "name": "positional_accuracy",
        "dataType": "TEXT",
        "examples": [
          "published report, method unknown",
          "company supplied location, method unknown"
        ],
        "required": false,
        "isGeometry": false,
        "description": "Description of location accuracy and method",
        "isIdentifier": false,
        "sourceFieldPatterns": [
          "positionalaccuracy",
          "accuracy",
          "location_method"
        ]
      },
      {
        "name": "source_distance",
        "dataType": "TEXT",
        "examples": [
          "metres",
          "3000 metres",
          "500 metres"
        ],
        "required": false,
        "isGeometry": false,
        "description": "Distance or scale information from source",
        "isIdentifier": false,
        "sourceFieldPatterns": [
          "source"
        ]
      },
      {
        "name": "occurrence_shape",
        "dataType": "TEXT",
        "required": false,
        "isGeometry": false,
        "description": "Shape or geometry description of the occurrence",
        "isIdentifier": false,
        "sourceFieldPatterns": [
          "mineraloccurrenceshape",
          "shape",
          "geometry_description"
        ]
      },
      {
        "name": "observation_method",
        "dataType": "TEXT",
        "required": false,
        "isGeometry": false,
        "description": "Method used to identify or classify the occurrence",
        "isIdentifier": false,
        "sourceFieldPatterns": [
          "observationmethod",
          "method",
          "classification_method"
        ]
      },
      {
        "name": "source_id",
        "dataType": "TEXT",
        "required": true,
        "isGeometry": false,
        "description": "Unique identifier from the source system",
        "isIdentifier": true,
        "sourceFieldPatterns": [
          "identifier",
          "id",
          "source_id",
          "_id"
        ]
      },
      {
        "name": "specification_uri",
        "dataType": "TEXT",
        "required": false,
        "isGeometry": false,
        "description": "URI reference to detailed specification",
        "isIdentifier": false,
        "sourceFieldPatterns": [
          "specification_uri",
          "uri",
          "reference_uri"
        ]
      },
      {
        "name": "commodity_uri",
        "dataType": "TEXT",
        "required": false,
        "isGeometry": false,
        "description": "URI reference to commodity classification",
        "isIdentifier": false,
        "sourceFieldPatterns": [
          "representativecommodity_uri",
          "commodity_uri"
        ]
      },
      {
        "name": "age_uri",
        "dataType": "TEXT",
        "required": false,
        "isGeometry": false,
        "description": "URI reference to geological age classification",
        "isIdentifier": false,
        "sourceFieldPatterns": [
          "representativeage_uri",
          "age_uri"
        ]
      },
      {
        "name": "geometry",
        "dataType": "GEOMETRY",
        "required": true,
        "isGeometry": true,
        "description": "Point location of the mineral occurrence",
        "isIdentifier": false,
        "sourceFieldPatterns": [
          "_geom",
          "geom",
          "geometry",
          "location"
        ]
      }
    ],
    "confidence": 0.95,
    "description": "A location where minerals have been identified, including prospects, deposits, mines, and mineralized zones",
    "geometryType": "POINT"
  }
}

{
  "fields": [
    {
      "name": "_id",
      "type": "string",
      "pattern": "ga_ozmin_[a-z0-9]+",
      "nullable": false,
      "description": "Unique identifier for each mineral occurrence record",
      "sampleValues": [
        "ga_ozmin_yk1x1b",
        "ga_ozmin_r8c28z",
        "ga_ozmin_cq0ltk"
      ]
    },
    {
      "name": "_geom",
      "type": "geometry",
      "pattern": "POINT\\([0-9.-]+ [0-9.-]+\\)",
      "nullable": false,
      "description": "Point geometry representing the location of the mineral occurrence",
      "sampleValues": [
        "POINT(143.9856 -37.2087)",
        "POINT(117.4462 -22.1176)",
        "POINT(122.0772 -28.765)"
      ]
    },
    {
      "name": "_featuretype",
      "type": "string",
      "nullable": true,
      "description": "Feature type classification (appears to be null in all samples)",
      "sampleValues": [
        null
      ]
    },
    {
      "name": "commodity",
      "type": "string",
      "nullable": true,
      "enumValues": [
        "Gold",
        "Iron"
      ],
      "description": "Primary commodity or mineral type found at the occurrence",
      "sampleValues": [
        "Gold",
        "Iron",
        null
      ]
    },
    {
      "name": "geologichistory",
      "type": "string",
      "nullable": true,
      "enumValues": [
        "Paleoproterozoic"
      ],
      "description": "Geological time period or era associated with the occurrence",
      "sampleValues": [
        null,
        "Paleoproterozoic"
      ]
    },
    {
      "name": "hostgeologicunit",
      "type": "string",
      "nullable": true,
      "description": "Name of the geological unit hosting the mineral occurrence",
      "sampleValues": [
        null
      ]
    },
    {
      "name": "hostgeologicunit_uri",
      "type": "string",
      "nullable": true,
      "description": "URI reference to the host geological unit",
      "sampleValues": [
        null
      ]
    },
    {
      "name": "identifier",
      "type": "string",
      "pattern": "http://pid\\.geoscience\\.gov\\.au/id/feature/ga/erl/mineraloccurrenceview/[0-9]+",
      "nullable": false,
      "description": "Persistent identifier URI for the mineral occurrence",
      "sampleValues": [
        "http://pid.geoscience.gov.au/id/feature/ga/erl/mineraloccurrenceview/340970"
      ]
    },
    {
      "name": "minename",
      "type": "string",
      "nullable": true,
      "description": "Name of the mine associated with the occurrence",
      "sampleValues": [
        null
      ]
    },
    {
      "name": "mine_uri",
      "type": "string",
      "nullable": true,
      "description": "URI reference to the associated mine",
      "sampleValues": [
        null
      ]
    },
    {
      "name": "mineraldepositmodel",
      "type": "string",
      "nullable": true,
      "description": "Model or type of mineral deposit",
      "sampleValues": [
        null
      ]
    },
    {
      "name": "mineraloccurrenceshape",
      "type": "string",
      "nullable": true,
      "description": "Shape or geometry type of the mineral occurrence",
      "sampleValues": [
        null
      ]
    },
    {
      "name": "mineraloccurrencetype",
      "type": "string",
      "nullable": false,
      "enumValues": [
        "mineralized zone"
      ],
      "description": "Type classification of the mineral occurrence",
      "sampleValues": [
        "mineralized zone"
      ]
    },
    {
      "name": "mineraloccurrencetype_uri",
      "type": "string",
      "nullable": true,
      "description": "URI reference to the mineral occurrence type",
      "sampleValues": [
        null
      ]
    },
    {
      "name": "name",
      "type": "string",
      "nullable": false,
      "description": "Name or label of the mineral occurrence",
      "sampleValues": [
        "Bosuns",
        "Blacksmith_Badger (hematite)",
        "Phoenix Ridge",
        "Blackall EPC 1398 (Recoverable)",
        "Chinese Howley"
      ]
    },
    {
      "name": "observationmethod",
      "type": "string",
      "pattern": "http://resource\\.geosciml\\.org/classifier/cgi/mineral-occurrence-type/[a-z-]+",
      "nullable": false,
      "description": "URI describing the method used to observe or classify the occurrence",
      "sampleValues": [
        "http://resource.geosciml.org/classifier/cgi/mineral-occurrence-type/mineralized-zone"
      ]
    },
    {
      "name": "positionalaccuracy",
      "type": "string",
      "nullable": true,
      "enumValues": [
        "State or NT agency supplied location, method unknown",
        "satellite image"
      ],
      "description": "Description of the accuracy or method used for positioning",
      "sampleValues": [
        null,
        "State or NT agency supplied location, method unknown",
        "satellite image"
      ]
    },
    {
      "name": "representativeage_uri",
      "type": "string",
      "nullable": true,
      "description": "URI reference to the representative geological age",
      "sampleValues": [
        null,
        "http://resource.geosciml.org/classifier/ics/ischart/Paleoproterozoic"
      ]
    },
    {
      "name": "representativecommodity_uri",
      "type": "string",
      "pattern": "http://resource\\.geosciml\\.org/classifier/cgi/commodity-code/[a-z]+",
      "nullable": true,
      "description": "URI reference to the representative commodity code",
      "sampleValues": [
        "http://resource.geosciml.org/classifier/cgi/commodity-code/gold",
        "http://resource.geosciml.org/classifier/cgi/commodity-code/iron",
        null
      ]
    },
    {
      "name": "representativeolderage_uri",
      "type": "string",
      "nullable": true,
      "description": "URI reference to the older age boundary",
      "sampleValues": [
        null,
        "http://resource.geosciml.org/classifier/ics/ischart/Paleoproterozoic"
      ]
    },
    {
      "name": "representativeyoungerage_uri",
      "type": "string",
      "nullable": true,
      "description": "URI reference to the younger age boundary",
      "sampleValues": [
        null,
        "http://resource.geosciml.org/classifier/ics/ischart/Paleoproterozoic"
      ]
    },
    {
      "name": "source",
      "type": "string",
      "pattern": "[0-9]* ?metres",
      "nullable": false,
      "description": "Source information or measurement unit (appears to contain distance measurements)",
      "sampleValues": [
        "metres",
        "1000 metres",
        "999 metres"
      ]
    },
    {
      "name": "specification_uri",
      "type": "string",
      "pattern": "http://pid\\.geoscience\\.gov\\.au/id/feature/ga/er/mineraloccurrence/[0-9]+",
      "nullable": false,
      "description": "URI reference to the detailed specification of the mineral occurrence",
      "sampleValues": [
        "http://pid.geoscience.gov.au/id/feature/ga/er/mineraloccurrence/340970"
      ]
    },
    {
      "name": "_mirrored_at",
      "type": "date",
      "pattern": "\\d{4}-\\d{2}-\\d{2} \\d{2}:\\d{2}:\\d{2}\\.\\d{6}\\+\\d{2}",
      "nullable": false,
      "description": "Timestamp when the record was mirrored or last updated",
      "sampleValues": [
        "2026-02-09 19:04:17.096238+00"
      ]
    },
    {
      "name": "geom",
      "type": "geometry",
      "nullable": false,
      "description": "Binary geometry data in Well-Known Binary (WKB) format",
      "sampleValues": [
        "0101000020E610000001DE02098AFF61406D567DAEB69A42C0"
      ]
    }
  ],
  "semantics": {
    "idFields": [
      "_id",
      "identifier",
      "specification_uri"
    ],
    "nameFields": [
      "name",
      "minename"
    ],
    "primaryKey": "_id",
    "statusFields": [
      "mineraloccurrencetype",
      "positionalaccuracy"
    ],
    "fieldMeanings": {
      "_id": "Primary key identifier",
      "geom": "Binary geometry data",
      "name": "Occurrence name/label",
      "_geom": "Point geometry coordinates",
      "source": "Source information with distance",
      "mine_uri": "Mine reference URI",
      "minename": "Associated mine name",
      "commodity": "Primary mineral commodity",
      "identifier": "Persistent identifier URI",
      "_featuretype": "Feature type classification",
      "_mirrored_at": "Data synchronization timestamp",
      "geologichistory": "Geological time period",
      "hostgeologicunit": "Host rock unit name",
      "observationmethod": "Classification method URI",
      "specification_uri": "Detailed specification reference",
      "positionalaccuracy": "Location accuracy description",
      "mineraldepositmodel": "Deposit model type",
      "hostgeologicunit_uri": "Host rock unit reference",
      "mineraloccurrencetype": "Occurrence classification",
      "representativeage_uri": "Representative age reference",
      "mineraloccurrenceshape": "Occurrence geometry shape",
      "mineraloccurrencetype_uri": "Occurrence type reference",
      "representativeolderage_uri": "Older age boundary reference",
      "representativecommodity_uri": "Commodity code reference",
      "representativeyoungerage_uri": "Younger age boundary reference"
    },
    "relationships": [
      {
        "field": "commodity",
        "relatedTo": "representativecommodity_uri",
        "relationshipType": "semantic_equivalent"
      },
      {
        "field": "geologichistory",
        "relatedTo": "representativeage_uri",
        "relationshipType": "semantic_equivalent"
      },
      {
        "field": "_geom",
        "relatedTo": "geom",
        "relationshipType": "format_variant"
      },
      {
        "field": "identifier",
        "relatedTo": "specification_uri",
        "relationshipType": "related_reference"
      }
    ],
    "geometryFields": [
      "_geom",
      "geom"
    ],
    "commodityFields": [
      "commodity",
      "representativecommodity_uri"
    ]
  },
  "confidence": 0.95,
  "entityType": "mineral_occurrence",
  "recordCount": 100
}

{
  "domain": "mining",
  "qualityNotes": [
    "Many fields have high null rates (geologichistory, hostgeologicunit, minename, etc.)",
    "Commodity field contains both single commodities and comma-separated lists",
    "Source field contains distance measurements but inconsistent units and formatting",
    "Positional accuracy information is often vague ('method unknown')",
    "URI fields provide structured references but may not be consistently populated",
    "Some records have no commodity information despite being mineral occurrences",
    "The mineraloccurrencetype_uri field sometimes contains company names instead of URIs"
  ],
  "commonPatterns": {
    "dateFields": [
      "_mirrored_at"
    ],
    "statusFields": [
      "mineraloccurrencetype"
    ],
    "geometryFields": [
      "_geom",
      "geom"
    ],
    "commodityFields": [
      "commodity",
      "representativecommodity_uri"
    ],
    "identifierFields": [
      "_id",
      "identifier",
      "specification_uri"
    ],
    "measurementFields": [
      "source"
    ]
  },
  "alternativeTypes": [],
  "primaryFeatureType": {
    "name": "Mineral Occurrence",
    "slug": "mineral_occurrence",
    "reasoning": "This data clearly represents mineral occurrences based on the 'mineraloccurrencetype' field with values like 'mineralized zone' and 'deposit', the presence of commodity information, and the point geometry representing specific locations where minerals have been found.",
    "attributes": [
      {
        "name": "name",
        "dataType": "TEXT",
        "examples": [
          "Falcon Magnetite BIF",
          "Mount Deans",
          "Mount Cooke East"
        ],
        "required": true,
        "isGeometry": false,
        "description": "Name of the mineral occurrence",
        "isIdentifier": false,
        "sourceFieldPatterns": [
          "name"
        ]
      },
      {
        "name": "occurrence_type",
        "dataType": "TEXT",
        "examples": [
          "mineralized zone",
          "deposit"
        ],
        "required": false,
        "enumValues": [
          "deposit",
          "mineralized zone",
          "prospect",
          "mine",
          "occurrence"
        ],
        "isGeometry": false,
        "description": "Type of mineral occurrence (deposit, mineralized zone, prospect, etc.)",
        "isIdentifier": false,
        "sourceFieldPatterns": [
          "mineraloccurrencetype",
          "occurrence_type",
          "deposit_type"
        ]
      },
      {
        "name": "commodities",
        "dataType": "TEXT",
        "examples": [
          "Iron",
          "Tin, Tantalum pentoxide, Tantalum, Lithium, Niobium, Niobium pentoxide",
          "Copper",
          "Gold"
        ],
        "required": false,
        "isGeometry": false,
        "description": "Comma-separated list of commodities present at this occurrence",
        "isIdentifier": false,
        "sourceFieldPatterns": [
          "commodity",
          "commodities",
          "minerals"
        ]
      },
      {
        "name": "primary_commodity",
        "dataType": "TEXT",
        "examples": [
          "iron",
          "tin",
          "copper",
          "gold"
        ],
        "required": false,
        "isGeometry": false,
        "description": "Primary or representative commodity",
        "isIdentifier": false,
        "sourceFieldPatterns": [
          "representativecommodity_uri",
          "primary_commodity",
          "main_commodity"
        ]
      },
      {
        "name": "geological_age",
        "dataType": "TEXT",
        "examples": [
          "Archean"
        ],
        "required": false,
        "isGeometry": false,
        "description": "Geological age or era of the occurrence",
        "isIdentifier": false,
        "sourceFieldPatterns": [
          "geologichistory",
          "geological_age",
          "age"
        ]
      },
      {
        "name": "host_rock",
        "dataType": "TEXT",
        "examples": [],
        "required": false,
        "isGeometry": false,
        "description": "Host geological unit or rock type",
        "isIdentifier": false,
        "sourceFieldPatterns": [
          "hostgeologicunit",
          "host_rock",
          "host_geology"
        ]
      },
      {
        "name": "deposit_model",
        "dataType": "TEXT",
        "examples": [],
        "required": false,
        "isGeometry": false,
        "description": "Mineral deposit model or type",
        "isIdentifier": false,
        "sourceFieldPatterns": [
          "mineraldepositmodel",
          "deposit_model",
          "deposit_type"
        ]
      },
      {
        "name": "mine_name",
        "dataType": "TEXT",
        "examples": [],
        "required": false,
        "isGeometry": false,
        "description": "Associated mine name if applicable",
        "isIdentifier": false,
        "sourceFieldPatterns": [
          "minename",
          "mine_name"
        ]
      },
      {
        "name": "positional_accuracy",
        "dataType": "TEXT",
        "examples": [
          "method unknown",
          "State or NT agency supplied location, method unknown"
        ],
        "required": false,
        "isGeometry": false,
        "description": "Description of positional accuracy",
        "isIdentifier": false,
        "sourceFieldPatterns": [
          "positionalaccuracy",
          "accuracy",
          "location_accuracy"
        ]
      },
      {
        "name": "source_distance",
        "dataType": "TEXT",
        "examples": [
          "500 metres",
          "100 metres",
          "2000 metres"
        ],
        "required": false,
        "isGeometry": false,
        "description": "Distance or scale information from source",
        "isIdentifier": false,
        "sourceFieldPatterns": [
          "source"
        ]
      },
      {
        "name": "geometry",
        "dataType": "GEOMETRY",
        "required": true,
        "isGeometry": true,
        "description": "Point location of the mineral occurrence",
        "isIdentifier": false,
        "sourceFieldPatterns": [
          "_geom",
          "geom",
          "geometry",
          "location"
        ]
      },
      {
        "name": "source_id",
        "dataType": "TEXT",
        "examples": [
          "ga_ozmin_lgrz8k",
          "ga_ozmin_h0p2lb"
        ],
        "required": true,
        "isGeometry": false,
        "description": "Unique identifier from source system",
        "isIdentifier": true,
        "sourceFieldPatterns": [
          "_id",
          "identifier",
          "id"
        ]
      },
      {
        "name": "source_url",
        "dataType": "TEXT",
        "examples": [
          "http://pid.geoscience.gov.au/id/feature/ga/er/mineraloccurrence/339433"
        ],
        "required": false,
        "isGeometry": false,
        "description": "URL or URI reference to source record",
        "isIdentifier": false,
        "sourceFieldPatterns": [
          "specification_uri",
          "identifier",
          "source_url"
        ]
      }
    ],
    "confidence": 0.95,
    "description": "A location where minerals have been identified, including prospects, deposits, mineralized zones, and mines",
    "geometryType": "POINT"
  }
}

{
  "fields": [
    {
      "name": "_id",
      "type": "string",
      "pattern": "ga_ozmin_[a-z0-9]+",
      "nullable": false,
      "description": "Unique identifier for each mineral occurrence record",
      "sampleValues": [
        "ga_ozmin_f5upxw",
        "ga_ozmin_7xc3p0",
        "ga_ozmin_r6vmb4"
      ]
    },
    {
      "name": "_geom",
      "type": "geometry",
      "pattern": "POINT\\([\\-\\d\\.\\s]+\\)",
      "nullable": false,
      "description": "Point geometry representing the location of the mineral occurrence",
      "sampleValues": [
        "POINT(121.2012 -30.9326)",
        "POINT(119.9546 -26.7562)",
        "POINT(146.44 -38.2)"
      ]
    },
    {
      "name": "_featuretype",
      "type": "string",
      "nullable": true,
      "description": "Feature type classification (appears to be null in all samples)",
      "sampleValues": [
        null
      ]
    },
    {
      "name": "commodity",
      "type": "string",
      "nullable": true,
      "enumValues": [
        "Gold"
      ],
      "description": "Primary commodity or mineral associated with the occurrence",
      "sampleValues": [
        null,
        "Gold",
        null
      ]
    },
    {
      "name": "geologichistory",
      "type": "string",
      "nullable": true,
      "enumValues": [
        "Archean"
      ],
      "description": "Geological time period or era of formation",
      "sampleValues": [
        "Archean",
        null
      ]
    },
    {
      "name": "hostgeologicunit",
      "type": "string",
      "nullable": true,
      "description": "Name of the geological unit hosting the mineral occurrence",
      "sampleValues": [
        null
      ]
    },
    {
      "name": "hostgeologicunit_uri",
      "type": "string",
      "nullable": true,
      "description": "URI reference to the host geological unit",
      "sampleValues": [
        null
      ]
    },
    {
      "name": "identifier",
      "type": "string",
      "pattern": "http://pid\\.geoscience\\.gov\\.au/id/feature/ga/erl/mineraloccurrenceview/\\d+",
      "nullable": false,
      "description": "Persistent identifier URI for the mineral occurrence",
      "sampleValues": [
        "http://pid.geoscience.gov.au/id/feature/ga/erl/mineraloccurrenceview/336603"
      ]
    },
    {
      "name": "minename",
      "type": "string",
      "nullable": true,
      "description": "Name of the mine associated with the occurrence",
      "sampleValues": [
        null
      ]
    },
    {
      "name": "mine_uri",
      "type": "string",
      "nullable": true,
      "description": "URI reference to the associated mine",
      "sampleValues": [
        null
      ]
    },
    {
      "name": "mineraldepositmodel",
      "type": "string",
      "nullable": true,
      "enumValues": [
        "unknown"
      ],
      "description": "Classification of the mineral deposit model",
      "sampleValues": [
        null,
        "unknown"
      ]
    },
    {
      "name": "mineraloccurrenceshape",
      "type": "string",
      "nullable": true,
      "description": "Shape or geometry type of the mineral occurrence",
      "sampleValues": [
        null
      ]
    },
    {
      "name": "mineraloccurrencetype",
      "type": "string",
      "nullable": false,
      "enumValues": [
        "mineralized zone",
        "deposit"
      ],
      "description": "Type classification of the mineral occurrence",
      "sampleValues": [
        "mineralized zone",
        "deposit"
      ]
    },
    {
      "name": "mineraloccurrencetype_uri",
      "type": "string",
      "nullable": true,
      "description": "URI reference to the mineral occurrence type or associated entity",
      "sampleValues": [
        null,
        "Blackham Resources Limited"
      ]
    },
    {
      "name": "name",
      "type": "string",
      "nullable": false,
      "description": "Name or title of the mineral occurrence",
      "sampleValues": [
        "Greenfields Extension",
        "Eagle",
        "APM Mill (GA Estimate)",
        "Doradilla",
        "Pawley"
      ]
    },
    {
      "name": "observationmethod",
      "type": "string",
      "pattern": "http://resource\\.geosciml\\.org/classifier/cgi/mineral-occurrence-type/[\\w\\-]+",
      "nullable": false,
      "description": "URI reference to the method used for observing/classifying the occurrence",
      "sampleValues": [
        "http://resource.geosciml.org/classifier/cgi/mineral-occurrence-type/mineralized-zone"
      ]
    },
    {
      "name": "positionalaccuracy",
      "type": "string",
      "nullable": true,
      "description": "Description of the positional accuracy or data source method",
      "sampleValues": [
        null,
        "State or NT agency supplied location, method unknown",
        "published report, method unknown"
      ]
    },
    {
      "name": "representativeage_uri",
      "type": "string",
      "pattern": "http://resource\\.geosciml\\.org/classifier/ics/ischart/\\w+",
      "nullable": true,
      "description": "URI reference to the representative geological age",
      "sampleValues": [
        "http://resource.geosciml.org/classifier/ics/ischart/Archean",
        null
      ]
    },
    {
      "name": "representativecommodity_uri",
      "type": "string",
      "pattern": "http://resource\\.geosciml\\.org/classifier/cgi/commodity-code/\\w+",
      "nullable": true,
      "description": "URI reference to the representative commodity",
      "sampleValues": [
        null,
        "http://resource.geosciml.org/classifier/cgi/commodity-code/gold"
      ]
    },
    {
      "name": "representativeolderage_uri",
      "type": "string",
      "nullable": true,
      "description": "URI reference to the older age boundary of the occurrence",
      "sampleValues": [
        "http://resource.geosciml.org/classifier/ics/ischart/Archean",
        null
      ]
    },
    {
      "name": "representativeyoungerage_uri",
      "type": "string",
      "nullable": true,
      "description": "URI reference to the younger age boundary of the occurrence",
      "sampleValues": [
        "http://resource.geosciml.org/classifier/ics/ischart/Archean",
        null
      ]
    },
    {
      "name": "source",
      "type": "string",
      "nullable": false,
      "description": "Source measurement or distance information",
      "sampleValues": [
        "metres",
        "999 metres",
        "10000 metres"
      ]
    },
    {
      "name": "specification_uri",
      "type": "string",
      "pattern": "http://pid\\.geoscience\\.gov\\.au/id/feature/ga/er/mineraloccurrence/\\d+",
      "nullable": false,
      "description": "URI reference to the detailed specification of the mineral occurrence",
      "sampleValues": [
        "http://pid.geoscience.gov.au/id/feature/ga/er/mineraloccurrence/336603"
      ]
    },
    {
      "name": "_mirrored_at",
      "type": "date",
      "pattern": "\\d{4}-\\d{2}-\\d{2} \\d{2}:\\d{2}:\\d{2}\\.\\d+\\+\\d{2}",
      "nullable": false,
      "description": "Timestamp when the record was mirrored or last updated",
      "sampleValues": [
        "2026-02-09 19:04:17.096238+00"
      ]
    },
    {
      "name": "geom",
      "type": "geometry",
      "pattern": "[0-9A-F]+",
      "nullable": false,
      "description": "Binary geometry data in hexadecimal format (PostGIS format)",
      "sampleValues": [
        "0101000020E610000022FDF675E04C5E40E63FA4DFBEEE3EC0"
      ]
    }
  ],
  "semantics": {
    "idFields": [
      "_id",
      "identifier",
      "specification_uri"
    ],
    "nameFields": [
      "name",
      "minename"
    ],
    "primaryKey": "_id",
    "statusFields": [
      "mineraloccurrencetype",
      "mineraldepositmodel"
    ],
    "fieldMeanings": {
      "_id": "Primary key identifier",
      "geom": "Binary geometry data",
      "name": "Occurrence name/title",
      "_geom": "Point geometry coordinates",
      "source": "Source measurement information",
      "mine_uri": "Mine reference URI",
      "minename": "Associated mine name",
      "commodity": "Primary mineral commodity",
      "identifier": "Persistent identifier URI",
      "_featuretype": "Feature type classification",
      "_mirrored_at": "Data synchronization timestamp",
      "geologichistory": "Geological time period",
      "hostgeologicunit": "Host rock unit name",
      "observationmethod": "Classification method reference",
      "specification_uri": "Detailed specification reference",
      "positionalaccuracy": "Location accuracy description",
      "mineraldepositmodel": "Deposit model classification",
      "hostgeologicunit_uri": "Host rock unit reference",
      "mineraloccurrencetype": "Occurrence type classification",
      "representativeage_uri": "Representative age reference",
      "mineraloccurrenceshape": "Occurrence geometry shape",
      "mineraloccurrencetype_uri": "Occurrence type reference",
      "representativeolderage_uri": "Older age boundary reference",
      "representativecommodity_uri": "Representative commodity reference",
      "representativeyoungerage_uri": "Younger age boundary reference"
    },
    "relationships": [
      {
        "field": "identifier",
        "relatedTo": "specification_uri",
        "relationshipType": "related_resource"
      },
      {
        "field": "commodity",
        "relatedTo": "representativecommodity_uri",
        "relationshipType": "semantic_reference"
      },
      {
        "field": "geologichistory",
        "relatedTo": "representativeage_uri",
        "relationshipType": "temporal_reference"
      },
      {
        "field": "_geom",
        "relatedTo": "geom",
        "relationshipType": "geometry_duplicate"
      }
    ],
    "geometryFields": [
      "_geom",
      "geom"
    ],
    "commodityFields": [
      "commodity",
      "representativecommodity_uri"
    ]
  },
  "confidence": 0.95,
  "entityType": "mineral_occurrence",
  "recordCount": 100
}