626bd3a095
- Apply Rule 39: RiC-O style hasOrHad*/isOrWas* for temporal slots - Apply Rule 43: Singular noun convention (keywords → keyword) - Update slot references to match renamed slot files - Maintain schema integrity across all class definitions
104 lines
3.4 KiB
YAML
104 lines
3.4 KiB
YAML
# ProvenanceBlock - Complete provenance tracking for the entry (supports both...
|
|
# Extracted from custodian_source.yaml per Rule 38 (modular schema files)
|
|
# Extraction date: 2026-01-08
|
|
|
|
id: https://nde.nl/ontology/hc/classes/ProvenanceBlock
|
|
name: ProvenanceBlock
|
|
title: ProvenanceBlock
|
|
|
|
prefixes:
|
|
linkml: https://w3id.org/linkml/
|
|
hc: https://nde.nl/ontology/hc/
|
|
schema: http://schema.org/
|
|
prov: http://www.w3.org/ns/prov#
|
|
xsd: http://www.w3.org/2001/XMLSchema#
|
|
|
|
imports:
|
|
- linkml:types
|
|
|
|
- ../enums/DataTierEnum
|
|
|
|
- ./DataTierSummary
|
|
- ./ProvenanceSources
|
|
default_range: string
|
|
|
|
classes:
|
|
ProvenanceBlock:
|
|
description: Complete provenance tracking for the entry (supports both nested and
|
|
flat formats)
|
|
attributes:
|
|
schema_version:
|
|
range: string
|
|
description: Version of the provenance schema
|
|
generated_at:
|
|
range: datetime
|
|
description: When provenance was generated
|
|
sources:
|
|
range: ProvenanceSources
|
|
description: Nested sources by type
|
|
data_tier_summary:
|
|
range: DataTierSummary
|
|
description: Summary of data tiers present
|
|
data_source:
|
|
range: string
|
|
description: Data source type (CSV_REGISTRY, API_SCRAPING, etc.)
|
|
data_sources:
|
|
range: string
|
|
multivalued: true
|
|
inlined_as_list: true
|
|
description: List of data sources (e.g., NDE registry, Google Maps, website)
|
|
data_tier:
|
|
range: DataTierEnum
|
|
description: Quality tier of the data
|
|
extraction_date:
|
|
range: string
|
|
description: When data was extracted (ISO datetime string, may lack timezone)
|
|
extraction_method:
|
|
range: string
|
|
description: Method used to extract the data
|
|
enrichment_date:
|
|
range: string
|
|
description: When enrichment was performed (ISO date string)
|
|
enrichment_method:
|
|
range: string
|
|
description: Method used to enrich the data (e.g., website_research)
|
|
confidence_score:
|
|
range: float
|
|
description: Confidence score (0-1)
|
|
note:
|
|
any_of:
|
|
- range: string
|
|
- range: string
|
|
multivalued: true
|
|
inlined_as_list: true
|
|
description: Provenance notes (can be single string or list)
|
|
source_url:
|
|
range: uri
|
|
description: URL of source data
|
|
fix_script:
|
|
range: string
|
|
description: Script used to fix this entry
|
|
last_manual_fix:
|
|
range: datetime
|
|
description: When last manual fix was applied
|
|
source_type:
|
|
range: string
|
|
description: Type of source (e.g., wikidata_p856)
|
|
discovery_timestamp:
|
|
range: datetime
|
|
description: When source was discovered
|
|
wikidata_id:
|
|
range: string
|
|
description: Wikidata entity ID
|
|
wikidata_property:
|
|
range: string
|
|
description: Wikidata property ID (e.g., P856)
|
|
archive_location:
|
|
range: string
|
|
description: Location of archived copy (e.g., web/1186/hartebrug.nl)
|
|
claim_extracted_from:
|
|
range: string
|
|
description: Source path from which claim was extracted (e.g., original_entry.reference)
|
|
verified_via_web_archive:
|
|
range: boolean
|
|
description: Whether claim was verified via web archive
|