350 lines
11 KiB
YAML
350 lines
11 KiB
YAML
id: https://w3id.org/heritage/custodian/hyponyms-curated
|
|
name: heritage-custodian-hyponyms-curated
|
|
title: Heritage Custodian Hyponyms Curated Schema
|
|
description: >-
|
|
Schema for manually curated Wikidata entity classifications for heritage institutions.
|
|
Documents entity types (hyponyms), geographic scope, temporal context, and classification
|
|
metadata for GLAMORCUBESFIXPHDNT taxonomy. Used as input for Wikidata enrichment pipeline.
|
|
|
|
license: https://creativecommons.org/publicdomain/zero/1.0/
|
|
version: 0.1.0
|
|
|
|
prefixes:
|
|
linkml: https://w3id.org/linkml/
|
|
heritage: https://w3id.org/heritage/custodian/
|
|
wikidata: http://www.wikidata.org/entity/
|
|
dcterms: http://purl.org/dc/terms/
|
|
prov: http://www.w3.org/ns/prov#
|
|
rico: https://www.ica.org/standards/RiC/ontology#
|
|
|
|
default_prefix: heritage
|
|
default_range: string
|
|
|
|
imports:
|
|
- linkml:types
|
|
|
|
# =============================================================================
|
|
# CORE CLASSES
|
|
# =============================================================================
|
|
|
|
classes:
|
|
HyponymsCurated:
|
|
description: >-
|
|
Root container for curated Wikidata entity classifications organized by
|
|
section type (hypernym, entity, entity_list, standards, collection, exclude).
|
|
tree_root: true
|
|
slots:
|
|
- sources
|
|
- hypernym
|
|
- entity
|
|
- entity_list
|
|
- standards
|
|
- collection
|
|
- exclude
|
|
slot_usage:
|
|
sources:
|
|
required: true
|
|
hypernym:
|
|
description: "Main classification section for entity types with hierarchical context"
|
|
multivalued: true
|
|
entity:
|
|
description: "Named entity classifications (single institutions, specific places)"
|
|
multivalued: true
|
|
entity_list:
|
|
description: "Category or list classifications (Wikipedia categories, Wikidata lists)"
|
|
multivalued: true
|
|
standards:
|
|
description: "Metadata standards, properties, or technical specifications"
|
|
multivalued: true
|
|
collection:
|
|
description: "Collection types or aggregation categories"
|
|
multivalued: true
|
|
exclude:
|
|
description: "Q-numbers explicitly excluded from taxonomy (no enrichment needed)"
|
|
multivalued: true
|
|
|
|
DataSource:
|
|
description: >-
|
|
Provenance metadata for source files (SPARQL queries, manual curation).
|
|
Documents where curated data originated and when it was created.
|
|
slots:
|
|
- label
|
|
- type
|
|
- date
|
|
slot_usage:
|
|
label:
|
|
required: true
|
|
description: "File path or URL of source data"
|
|
type:
|
|
required: true
|
|
description: "Type of source (sparql_results, sparql_query, manual_curation)"
|
|
date:
|
|
required: true
|
|
description: "Timestamp when source was created (ISO 8601 format)"
|
|
|
|
CuratedEntity:
|
|
description: >-
|
|
Base class for curated entity metadata. Contains manual classifications
|
|
including geographic scope, temporal context, GLAMORCUBESFIXPHDNT type codes,
|
|
and hierarchical hypernyms.
|
|
slots:
|
|
- label
|
|
- hypernym
|
|
- type
|
|
- country
|
|
- subregion
|
|
- settlement
|
|
- time
|
|
- duplicate
|
|
- rico
|
|
- notes
|
|
slot_usage:
|
|
label:
|
|
required: true
|
|
identifier: true
|
|
description: "Wikidata Q-number (e.g., Q12345) or other identifier"
|
|
pattern: '^(Q[0-9]+|P[0-9]+|Category:.+|List_of_.+)$'
|
|
hypernym:
|
|
description: "Parent concept(s) in taxonomy hierarchy"
|
|
multivalued: true
|
|
comments:
|
|
- "Example: ['museum', 'art institution']"
|
|
- "Multiple hypernyms for multi-faceted entities"
|
|
type:
|
|
description: "GLAMORCUBESFIXPHDNT type code(s)"
|
|
multivalued: true
|
|
range: GlamTypeCode
|
|
comments:
|
|
- "Allowed: G, L, A, M, O, R, C, U, B, E, S, F, I, X, P, H, D, N, T"
|
|
country:
|
|
description: "Geographic scope: country name(s)"
|
|
multivalued: true
|
|
comments:
|
|
- "Use for entities specific to one or more countries"
|
|
- "Example: ['Netherlands', 'Belgium']"
|
|
subregion:
|
|
description: "Geographic scope: subregion, province, or state"
|
|
multivalued: true
|
|
comments:
|
|
- "Example: ['North Holland', 'Utrecht']"
|
|
- "More granular than country, less than settlement"
|
|
settlement:
|
|
description: "Geographic scope: city, town, or locality"
|
|
multivalued: true
|
|
comments:
|
|
- "Example: ['Amsterdam', 'Rotterdam']"
|
|
- "Most specific geographic level"
|
|
time:
|
|
description: "Temporal scope: time period(s) this entity applies to"
|
|
multivalued: true
|
|
range: TemporalScope
|
|
comments:
|
|
- "Use for historically bounded concepts"
|
|
- "Example: 17th century museums, 1960s art centers"
|
|
duplicate:
|
|
description: "Flag indicating entity is a duplicate of another Q-number"
|
|
range: boolean
|
|
comments:
|
|
- "Set to true if this entity duplicates another in the taxonomy"
|
|
rico:
|
|
description: "Records in Contexts (RiC-O) classification"
|
|
multivalued: true
|
|
comments:
|
|
- "Example: ['recordSetTypes'] for archival record types"
|
|
notes:
|
|
description: "Free-text notes about curation decisions or entity ambiguity"
|
|
|
|
TemporalScope:
|
|
description: >-
|
|
Temporal context for an entity. Specifies the time period an entity
|
|
applies to or was active during, with start/end markers.
|
|
slots:
|
|
- label
|
|
- type
|
|
slot_usage:
|
|
label:
|
|
required: true
|
|
description: "Human-readable time period label"
|
|
comments:
|
|
- "Example: '17th century', '1960s', 'Medieval period'"
|
|
type:
|
|
description: "List of temporal markers (start, end, point)"
|
|
multivalued: true
|
|
range: TemporalMarker
|
|
comments:
|
|
- "Use 'start' for beginning of period"
|
|
- "Use 'end' for terminus of period"
|
|
- "Use 'point' for specific date/year"
|
|
|
|
TemporalMarker:
|
|
description: >-
|
|
Marker indicating temporal position (start, end, or point in time).
|
|
slots:
|
|
- label
|
|
slot_usage:
|
|
label:
|
|
required: true
|
|
range: TemporalMarkerEnum
|
|
description: "Type of temporal marker: start, end, or point"
|
|
|
|
# =============================================================================
|
|
# SLOTS
|
|
# =============================================================================
|
|
|
|
slots:
|
|
# Root container slots
|
|
sources:
|
|
description: "List of data sources for curated entities"
|
|
range: DataSource
|
|
multivalued: true
|
|
inlined_as_list: true
|
|
slot_uri: prov:wasDerivedFrom
|
|
|
|
hypernym:
|
|
description: "Main classification section for hyponyms with hierarchical context"
|
|
range: CuratedEntity
|
|
multivalued: true
|
|
inlined_as_list: true
|
|
|
|
entity:
|
|
description: "Named entity classifications"
|
|
range: CuratedEntity
|
|
multivalued: true
|
|
inlined_as_list: true
|
|
|
|
entity_list:
|
|
description: "Category or list classifications"
|
|
range: CuratedEntity
|
|
multivalued: true
|
|
inlined_as_list: true
|
|
|
|
standards:
|
|
description: "Metadata standards and properties"
|
|
range: CuratedEntity
|
|
multivalued: true
|
|
inlined_as_list: true
|
|
|
|
collection:
|
|
description: "Collection types and aggregation categories"
|
|
range: CuratedEntity
|
|
multivalued: true
|
|
inlined_as_list: true
|
|
|
|
exclude:
|
|
description: "Q-numbers excluded from taxonomy (plain list)"
|
|
range: string
|
|
multivalued: true
|
|
pattern: '^Q[0-9]+$'
|
|
comments:
|
|
- "No enrichment performed on excluded entities"
|
|
|
|
# DataSource slots
|
|
label:
|
|
description: "Identifier, file path, or time period label"
|
|
range: string
|
|
identifier: true
|
|
|
|
type:
|
|
description: "Type classification (data source type, temporal marker, GLAM type)"
|
|
range: string
|
|
|
|
date:
|
|
description: "Date or timestamp (ISO 8601 format)"
|
|
range: string
|
|
pattern: '^[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2}Z$'
|
|
comments:
|
|
- "Format: YYYY-MM-DDTHH:mm:ssZ"
|
|
|
|
# CuratedEntity slots
|
|
country:
|
|
description: "Country name(s) for geographic scope"
|
|
range: string
|
|
multivalued: true
|
|
|
|
subregion:
|
|
description: "Subregion, province, or state name(s)"
|
|
range: string
|
|
multivalued: true
|
|
|
|
settlement:
|
|
description: "City, town, or locality name(s)"
|
|
range: string
|
|
multivalued: true
|
|
|
|
time:
|
|
description: "Temporal scope: time period(s)"
|
|
range: TemporalScope
|
|
multivalued: true
|
|
|
|
duplicate:
|
|
description: "Flag for duplicate entities"
|
|
range: boolean
|
|
|
|
rico:
|
|
description: "Records in Contexts (RiC-O) classification"
|
|
range: string
|
|
multivalued: true
|
|
slot_uri: rico:hasRecordSetType
|
|
|
|
notes:
|
|
description: "Free-text curation notes"
|
|
range: string
|
|
|
|
# =============================================================================
|
|
# ENUMERATIONS
|
|
# =============================================================================
|
|
|
|
enums:
|
|
GlamTypeCode:
|
|
description: >-
|
|
GLAMORCUBESFIXPHDNT taxonomy type codes (19 types).
|
|
Single-letter codes for heritage institution classification.
|
|
permissible_values:
|
|
G:
|
|
description: "Gallery - Art gallery or exhibition space"
|
|
L:
|
|
description: "Library - Public, academic, or specialized library"
|
|
A:
|
|
description: "Archive - Government, corporate, or personal archive"
|
|
M:
|
|
description: "Museum - Art, history, science, or specialized museum"
|
|
O:
|
|
description: "Official Institution - Government heritage agencies"
|
|
R:
|
|
description: "Research Center - Research institutes and documentation centers"
|
|
C:
|
|
description: "Corporation - Corporate heritage collections"
|
|
U:
|
|
description: "Unknown - Institution type cannot be determined"
|
|
B:
|
|
description: "Botanical/Zoo - Botanical gardens and zoological parks"
|
|
E:
|
|
description: "Education Provider - Educational institutions with collections"
|
|
S:
|
|
description: "Collecting Society - Societies collecting specialized materials"
|
|
F:
|
|
description: "Features - Physical landscape features with heritage significance"
|
|
I:
|
|
description: "Intangible Heritage Group - Organizations preserving intangible heritage"
|
|
X:
|
|
description: "Mixed - Multiple types (uses X code)"
|
|
P:
|
|
description: "Personal Collection - Private personal collections"
|
|
H:
|
|
description: "Holy Sites - Religious heritage sites and institutions"
|
|
D:
|
|
description: "Digital Platform - Digital heritage platforms and repositories"
|
|
N:
|
|
description: "NGO - Non-governmental heritage organizations"
|
|
T:
|
|
description: "Taste/Smell - Culinary and olfactory heritage institutions"
|
|
|
|
TemporalMarkerEnum:
|
|
description: "Type of temporal marker"
|
|
permissible_values:
|
|
start:
|
|
description: "Beginning of time period"
|
|
end:
|
|
description: "End of time period"
|
|
point:
|
|
description: "Specific point in time"
|