102 lines
3.6 KiB
YAML
102 lines
3.6 KiB
YAML
id: https://nde.nl/ontology/hc/classes/Provenance
|
|
name: Provenance
|
|
title: Provenance
|
|
prefixes:
|
|
linkml: https://w3id.org/linkml/
|
|
hc: https://nde.nl/ontology/hc/
|
|
prov: http://www.w3.org/ns/prov#
|
|
dct: http://purl.org/dc/terms/
|
|
schema: http://schema.org/
|
|
xsd: http://www.w3.org/2001/XMLSchema#
|
|
dcterms: http://purl.org/dc/terms/
|
|
crm: http://www.cidoc-crm.org/cidoc-crm/
|
|
skos: http://www.w3.org/2004/02/skos/core#
|
|
rdfs: http://www.w3.org/2000/01/rdf-schema#
|
|
org: http://www.w3.org/ns/org#
|
|
imports:
|
|
- ./LLMResponse
|
|
- ./RetrievalMethod
|
|
- ../slots/has_note
|
|
- linkml:types
|
|
- ../slots/has_agent
|
|
- ../slots/identified_by
|
|
- ../slots/has_output
|
|
- ../slots/has_quantity
|
|
- ../slots/based_on
|
|
- ../slots/generated_by
|
|
- ../slots/retrieved_by
|
|
- ../slots/retrieved_through
|
|
- ../slots/temporal_extent
|
|
# default_range: string
|
|
classes:
|
|
Provenance:
|
|
description: 'A single provenance statement describing the origin, lineage, or
|
|
derivation of a piece of data.
|
|
|
|
**DISTINCTION FROM ProvenanceBlock**: - `Provenance` represents a SINGLE provenance
|
|
statement (one source, one activity) - `ProvenanceBlock` bundles MULTIPLE provenance
|
|
sources together
|
|
|
|
Use `Provenance` when: - Tracking provenance of individual data elements - Recording
|
|
specific extraction or transformation activities - Linking data to its source
|
|
agent/entity
|
|
|
|
**ONTOLOGY MAPPING**: - class_uri: prov:Activity (the extraction/derivation
|
|
activity) - Links to prov:Agent via has_agent - Links to prov:Entity
|
|
via used (source) and generated (result)'
|
|
class_uri: prov:Activity
|
|
close_mappings:
|
|
- dct:ProvenanceStatement
|
|
- schema:Action
|
|
related_mappings:
|
|
- prov:Entity
|
|
- prov:Derivation
|
|
slots:
|
|
- has_agent
|
|
- temporal_extent
|
|
- generated_by
|
|
- retrieved_by
|
|
- retrieved_through
|
|
- identified_by
|
|
- has_quantity
|
|
- based_on
|
|
- has_output
|
|
- has_note
|
|
slot_usage:
|
|
retrieved_by:
|
|
# range: string
|
|
inlined: false # Fixed invalid inline for primitive type
|
|
retrieved_through:
|
|
range: RetrievalMethod
|
|
inlined: true
|
|
temporal_extent: null
|
|
identified_by:
|
|
# range: string # uriorcurie
|
|
has_quantity:
|
|
range: integer
|
|
inlined: false # Fixed invalid inline for primitive type
|
|
based_on:
|
|
# range: string # uriorcurie
|
|
multivalued: true
|
|
has_output:
|
|
range: LLMResponse
|
|
inlined: true
|
|
annotations:
|
|
custodian_types: '["*"]'
|
|
custodian_types_rationale: Provenance tracking is universal across all custodian
|
|
types.
|
|
custodian_types_primary: '*'
|
|
specificity_score: 0.15
|
|
specificity_rationale: Very low specificity - provenance metadata applies universally.
|
|
examples:
|
|
- value: "Provenance:\n extraction_method: \"xpath_extraction\"\n source_entity:\
|
|
\ \"https://example.org/webpage/12345\"\n generated_by:\n has_score:\n\
|
|
\ has_score: 0.95\n has_method: \"xpath_extraction\"\
|
|
\n has_description: \"Exact match at expected XPath\"\n note:\
|
|
\ \"Extracted from archived HTML using XPath\"\n"
|
|
- value: "Provenance:\n retrieved_by:\n has_label: \"claude-opus-4.5\"\
|
|
\n retrieved_through:\n has_label: \"exa_crawling_exa\"\
|
|
\n based_on:\n - \"https://www.linkedin.com/in/...\"\n identified_by:\
|
|
\ \"exa_12345678\"\n has_quantity:\n quantity_value: 0.001\n \
|
|
\ has_unit:\n has_label: \"USD\"\n temporal_extent:\n\
|
|
\ begin_of_the_begin: \"2025-12-12T22:00:00Z\"\n"
|