id: https://nde.nl/ontology/hc/class/ExtractionMetadata
name: ExtractionMetadata
title: Extraction Metadata Class
prefixes:
  linkml: https://w3id.org/linkml/
  hc: https://nde.nl/ontology/hc/
  schema: http://schema.org/
  prov: http://www.w3.org/ns/prov#
  dct: http://purl.org/dc/terms/
default_prefix: hc
imports:
  - linkml:types
  - ../enums/ProfileExtractionMethodEnum
  - ../metadata
  - ../slots/has_source
  - ../slots/identified_by
  - ../slots/retrieved_at
  - ../slots/retrieved_by
  - ../slots/has_method
  - ../slots/has_url
  - ../slots/has_expense
  - ../slots/has_provenance
  - ../slots/has_score
classes:
  ExtractionMetadata:
    class_uri: prov:Activity
    description: Provenance metadata describing how and when extraction was performed.
    exact_mappings:
      - prov:Activity
    close_mappings:
      - schema:Action
      - dct:ProvenanceStatement
    slots:
      - has_source
      - identified_by
      - retrieved_at
      - retrieved_by
      - has_method
      - has_url
      - has_expense
      - has_provenance
      - has_score
    slot_usage:
      retrieved_at:
        range: datetime
        required: true
      has_method:
        range: ProfileExtractionMethodEnum
        required: true
      has_url:
        range: uri
      has_expense:
        range: float
        minimum_value: 0.0
    see_also:
      - https://www.linkedin.com/in/...\
    notes:
      - |
        Preserved from prior description (commit ee5e8e5a):

        Preserved from prior description (commit ee5e8e5a):

        "Provenance metadata for data extraction activities.\n\nRecords how, when, and by what agent data was extracted from \nexternal sources (LinkedIn, web scraping, APIs).\n\n**PROV-O Alignment**:\n- ExtractionMetadata IS a prov:Activity (the extraction process)\n- The extracted data IS the prov:Entity (output of the activity)\n- retrieved_by IS the prov:Agent (software/AI that performed extraction)\n- has_source/has_url IS prov:used (input to the activity)\n\n**Use Cases**:\n- LinkedIn profile extractions via Exa API\n- Web scraping provenance\n- Staff list parsing provenance\n- Connection network extraction\n\n**Example JSON Structure**:\n```json\n{\n  \"extraction_metadata\": {\n    \"has_source\": \"/path/to/source.json\",\n    \"identified_by\": \"org_staff_0001_name\",\n    \"retrieval_timestamp\": \"2025-12-12T22:00:00Z\",\n    \"has_method\": \"exa_crawling_exa\",\n    \"retrieved_by\": \"claude-opus-4.5\",\n    \"has_url\": \"https://www.linkedin.com/in/...\"\
    annotations:
      specificity_score: 0.5
      specificity_rationale: Provenance activity record for extraction pipelines and auditability.
      custodian_types: '["*"]'