147 lines
5.6 KiB
YAML
147 lines
5.6 KiB
YAML
id: https://nde.nl/ontology/hc/class/ExtractionMetadata
|
|
name: extraction_metadata_class
|
|
title: Extraction Metadata Class
|
|
version: 1.0.0
|
|
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/
|
|
xsd: http://www.w3.org/2001/XMLSchema#
|
|
imports:
|
|
- linkml:types
|
|
- ../metadata
|
|
- ./LLMResponse
|
|
- ./SpecificityAnnotation
|
|
- ./TemplateSpecificityScore
|
|
- ./TemplateSpecificityType
|
|
- ./TemplateSpecificityTypes
|
|
- ../enums/ProfileExtractionMethodEnum
|
|
- ../slots/extraction_agent
|
|
- ../slots/extraction_method
|
|
- ../slots/cost_usd
|
|
- ../slots/source_file
|
|
- ../slots/staff_id
|
|
- ../slots/extraction_date
|
|
- ../slots/linkedin_url
|
|
- ../slots/request_id
|
|
- ../slots/llm_response
|
|
- ../slots/specificity_annotation
|
|
- ../slots/has_or_had_score
|
|
- ../slots/cost_usd
|
|
- ../slots/extraction_agent
|
|
- ../slots/extraction_date
|
|
- ../slots/extraction_method
|
|
- ../slots/linkedin_url
|
|
- ../slots/llm_response
|
|
- ../slots/request_id
|
|
- ../slots/source_file
|
|
- ../slots/specificity_annotation
|
|
- ../slots/staff_id
|
|
- ../slots/has_or_had_score
|
|
- ../slots/cost_usd
|
|
- ../slots/extraction_agent
|
|
- ../slots/extraction_date
|
|
- ../slots/extraction_method
|
|
- ../slots/linkedin_url
|
|
- ../slots/llm_response
|
|
- ../slots/request_id
|
|
- ../slots/source_file
|
|
- ../slots/specificity_annotation
|
|
- ../slots/staff_id
|
|
- ../slots/has_or_had_score
|
|
default_range: string
|
|
classes:
|
|
ExtractionMetadata:
|
|
class_uri: prov:Activity
|
|
description: "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- extraction_agent IS the prov:Agent (software/AI that performed extraction)\n- source_file/linkedin_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 \"source_file\": \"/path/to/source.json\",\n \"staff_id\": \"org_staff_0001_name\",\n \"extraction_date\": \"2025-12-12T22:00:00Z\",\n \"extraction_method\": \"exa_crawling_exa\",\n \"extraction_agent\": \"claude-opus-4.5\",\n \"linkedin_url\": \"https://www.linkedin.com/in/...\"\
|
|
,\n \"cost_usd\": 0.001\n }\n}\n```\n"
|
|
exact_mappings:
|
|
- prov:Activity
|
|
close_mappings:
|
|
- schema:Action
|
|
- dct:ProvenanceStatement
|
|
slots:
|
|
- cost_usd
|
|
- extraction_agent
|
|
- extraction_date
|
|
- extraction_method
|
|
- linkedin_url
|
|
- llm_response
|
|
- request_id
|
|
- source_file
|
|
- specificity_annotation
|
|
- staff_id
|
|
- has_or_had_score
|
|
slot_usage:
|
|
source_file:
|
|
range: string
|
|
examples:
|
|
- value: /data/custodian/person/affiliated/parsed/rijksmuseum_staff_20251210T155416Z.json
|
|
description: Path to parsed staff list JSON
|
|
staff_id:
|
|
range: string
|
|
pattern: ^[a-z0-9-]+_staff_[a-z0-9-_]+$
|
|
examples:
|
|
- value: rijksmuseum_staff_0042_jan_van_der_berg
|
|
description: Staff ID with org prefix, index, and name slug
|
|
extraction_date:
|
|
range: datetime
|
|
required: true
|
|
examples:
|
|
- value: '2025-12-12T22:00:00Z'
|
|
description: UTC timestamp of extraction
|
|
extraction_method:
|
|
range: ProfileExtractionMethodEnum
|
|
required: true
|
|
examples:
|
|
- value: exa_crawling_exa
|
|
description: Extracted via Exa AI crawling API
|
|
extraction_agent:
|
|
range: string
|
|
examples:
|
|
- value: claude-opus-4.5
|
|
description: Extracted by Claude Opus 4.5
|
|
- value: ''
|
|
description: Empty string for fully automated extraction
|
|
linkedin_url:
|
|
range: uri
|
|
pattern: ^https://www\.linkedin\.com/in/[a-z0-9-]+/?$
|
|
examples:
|
|
- value: https://www.linkedin.com/in/jan-van-der-berg-12345
|
|
description: LinkedIn profile URL
|
|
cost_usd:
|
|
range: float
|
|
minimum_value: 0.0
|
|
examples:
|
|
- value: 0.001
|
|
description: Exa API call cost
|
|
- value: 0.0
|
|
description: Free extraction (cached/local)
|
|
request_id:
|
|
range: string
|
|
examples:
|
|
- value: exa_12345678-abcd-efgh-ijkl-mnopqrstuv
|
|
description: Exa API request ID
|
|
llm_response:
|
|
range: LLMResponse
|
|
required: false
|
|
inlined: true
|
|
examples:
|
|
- value: "{\n \"content\": \"Extracted institution data...\",\n \"reasoning_content\": \"Analyzing the input for LinkML schema conformity...\",\n \"thinking_mode\": \"preserved\",\n \"clear_thinking\": false,\n \"model\": \"glm-4.7\",\n \"provider\": \"zai\",\n \"created\": \"2025-12-23T10:30:00Z\",\n \"prompt_tokens\": 150,\n \"completion_tokens\": 450,\n \"total_tokens\": 600,\n \"finish_reason\": \"stop\",\n \"cost_usd\": 0.0\n}\n"
|
|
description: GLM 4.7 response with Preserved Thinking for extraction
|
|
comments:
|
|
- Every person entity file MUST have extraction_metadata
|
|
- See AGENTS.md Rule 20 for required fields
|
|
- extraction_agent should be 'claude-opus-4.5' for manual extraction
|
|
- cost_usd enables budget tracking for API-heavy extractions
|
|
see_also:
|
|
- https://www.w3.org/TR/prov-o/
|
|
- https://docs.exa.ai/
|
|
annotations:
|
|
specificity_score: 0.1
|
|
specificity_rationale: Generic utility class/slot created during migration
|
|
custodian_types:
|
|
- '*'
|
|
custodian_types_rationale: Universal utility concept
|