glam/data/custodian.backup.20251230/CZ-10-BRN-A-NPUB.yaml
2025-12-30 23:07:03 +01:00

260 lines
9.7 KiB
YAML

original_entry:
name: Národní památkový ústav Brno
institution_type: ARCHIVE
source: CH-Annotator (czech_unified_ch_annotator.yaml)
identifiers:
- &id001
identifier_scheme: ARON_UUID
identifier_value: 8032d5a7-4ec2-4848-ad77-a74a498b5a5e
identifier_url: https://portal.nacr.cz/aron/apu/8032d5a7-4ec2-4848-ad77-a74a498b5a5e
- &id002
identifier_scheme: INSTITUTION_CODE
identifier_value: '906202080'
- &id003
identifier_scheme: Wikidata
identifier_value: Q114617788
identifier_url: https://www.wikidata.org/wiki/Q114617788
locations: []
processing_timestamp: '2025-12-06T23:37:44.357097+00:00'
ghcid:
ghcid_current: CZ-10-BRN-A-NPUB
ghcid_original: XX-XX-XXX-A-NPÚB
ghcid_uuid: 5bd9d193-990d-50db-a565-cae0c4b87c26
ghcid_uuid_sha256: 54ffadfb-428e-82dd-b4da-5702b300ae18
ghcid_numeric: 6124805312912179933
record_id: a265e764-ea26-4772-94ff-b6c03e7efcf8
generation_timestamp: '2025-12-06T23:37:44.357097+00:00'
location_resolution:
country_code: CZ
region_code: '10'
city_code: BRN
method: CH_ANNOTATOR_TOP_SET
resolution_timestamp: '2025-12-07T00:20:05.271885+00:00'
region_name: CZ-10
iso_code_source: CZ-10
city_name: Brno
geonames_id: 3078610
feature_code: PPLA
extracted_toponym: Brno
latitude: 49.19522
longitude: 16.60796
ghcid_history:
- ghcid: CZ-10-BRN-A-NPUB
ghcid_numeric: 6124805312912179933
valid_from: '2025-12-08T11:21:34.219628+00:00'
reason: 'Normalized diacritics to ASCII per ABBREV-DIACRITICS rule (was: CZ-10-BRN-A-NPÚB)'
- ghcid: XX-XX-XXX-A-NPÚB
ghcid_numeric: 11065478675602490894
valid_from: '2025-12-06T23:37:44.357097+00:00'
reason: Initial GHCID from CH-Annotator (czech_unified_ch_annotator.yaml)
valid_to: '2025-12-08T11:21:34.219628+00:00'
- ghcid: CZ-XX-XXX-A-NPÚB
valid_from: '2025-12-06T23:54:39.144508+00:00'
reason: 'Country resolved via Wikidata P17: XX→CZ'
- ghcid: CZ-10-XXX-A-NPÚB
valid_from: '2025-12-07T00:01:56.325884+00:00'
reason: 'Region resolved via Wikidata P131: XX->10 (CZ-10)'
- ghcid: CZ-10-BRN-A-NPÚB
valid_from: '2025-12-07T00:20:05.271890+00:00'
reason: 'Location resolved via CH-Annotator TOP.SET extraction: Brno -> Brno (GeoNames:3078610)'
custodian_name:
claim_type: custodian_name
claim_value: Národní památkový ústav Brno
source_type: ch_annotator
identifiers:
- identifier_scheme: GHCID
identifier_value: CZ-10-BRN-A-NPUB
- identifier_scheme: GHCID_UUID
identifier_value: 5bd9d193-990d-50db-a565-cae0c4b87c26
- identifier_scheme: GHCID_UUID_SHA256
identifier_value: 54ffadfb-428e-82dd-b4da-5702b300ae18
- identifier_scheme: GHCID_NUMERIC
identifier_value: '6124805312912179933'
- identifier_scheme: RECORD_ID
identifier_value: a265e764-ea26-4772-94ff-b6c03e7efcf8
- *id001
- *id002
- *id003
provenance:
data_source: API_SCRAPING
data_tier: TIER_1_AUTHORITATIVE
extraction_date: '2025-11-19T11:35:45.744576+00:00'
extraction_method: 'Created from CH-Annotator file: czech_unified_ch_annotator.yaml'
confidence_score: 0.85
notes:
- 'Country resolved 2025-12-06T23:54:39Z: XX→CZ via Wikidata P17'
- 'Region resolved 2025-12-07T00:01:56Z: XX->10 via Wikidata P131 (CZ-10)'
- 'Location resolved 2025-12-07T00:20:05Z: CH-Annotator TOP.SET extraction ''Brno'' -> Brno (GeoNames:3078610, Region:64)'
- Removed incorrect wikidata_enrichment on 2025-12-08T08:18:45.439025+00:00. Re-enrichment required with proper matching.
- 'YouTube/Google Maps enrichment 2025-12-08T19:44:49Z: Maps: rejected by LLM; YouTube: not found'
- Canonical location added via normalize_custodian_files.py on 2025-12-08T23:48:03Z
- Canonical location added via normalize_custodian_files.py on 2025-12-09T06:49:27Z
schema_version: 2.0.0
enrichment_provenance:
wikidata_enrichment:
content_hash: sha256-WkZ1IVzH+6U6fO70CHXOu3KC0YYXK4oJctvQefhzYxo=
verified_at: '2025-12-28T19:58:20.609644+00:00'
wasDerivedFrom: https://www.wikidata.org/wiki/Q114617788
provenance_schema_version: '2.0'
standards_compliance:
- W3C PROV-O
- W3C SRI (content hashes)
generated_at: '2025-12-28T19:58:20.609667+00:00'
ch_annotator:
convention_id: ch_annotator-v1_7_0
convention_version: 1.7.0
entity_classification:
hypernym: GRP
hypernym_label: GROUP
subtype: GRP.HER.ARC
subtype_label: ARCHIVE
ontology_class: schema:ArchiveOrganization
alternative_classes:
- org:FormalOrganization
- rov:RegisteredOrganization
- glam:HeritageCustodian
extraction_provenance:
namespace: glam
path: /files/czech_unified.yaml
timestamp: '2025-11-19T11:35:45.744576+00:00'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
annotation_provenance:
annotation_agent: opencode-claude-sonnet-4
annotation_date: '2025-12-06T21:12:32.389491+00:00'
annotation_method: retroactive CH-Annotator application via batch script
source_file: czech_unified.yaml
annotation_metadata:
confidence_score: 0.85
verified: false
verification_date:
verified_by:
entity_claims:
- claim_type: full_name
claim_value: Národní památkový ústav Brno
property_uri: skos:prefLabel
provenance:
namespace: glam
path: /files/czech_unified.yaml
timestamp: '2025-11-19T11:35:45.744576+00:00'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
confidence: 0.85
- claim_type: institution_type
claim_value: ARCHIVE
property_uri: rdf:type
provenance:
namespace: glam
path: /files/czech_unified.yaml
timestamp: '2025-11-19T11:35:45.744576+00:00'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
confidence: 0.95
- claim_type: wikidata_id
claim_value: Q114617788
property_uri: owl:sameAs
provenance:
namespace: wikidata
path: /entity/Q114617788
timestamp: '2025-11-19T11:35:45.744576+00:00'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
confidence: 0.98
- claim_type: location_settlement
claim_value: Brno
property_uri: schema:location
hypernym_code: TOP.SET
hypernym_label: SETTLEMENT
provenance:
namespace: geonames
path: /geonames/3078610
timestamp: '2025-12-07T00:20:05.271893+00:00'
agent: extract_locations_ch_annotator.py
context_convention: ch_annotator-v1_7_0
confidence: 0.85
extraction_source:
field: institution_name
extracted_text: Brno
method: pattern_matching
integration_note:
created_from: czech_unified_ch_annotator.yaml
creation_date: '2025-12-06T23:37:44.357097+00:00'
creation_method: create_custodian_from_ch_annotator.py
wikidata_enrichment:
wikidata_entity_id: Q114617788
api_metadata:
api_endpoint: https://www.wikidata.org/w/rest.php/wikibase/v1
fetch_timestamp: '2025-12-08T23:41:01.955159+00:00'
user_agent: GLAMDataExtractor/1.1 (glam-data@example.com) Python/httpx
enrichment_version: 2.0_full
properties_found:
- P31
- P17
- P159
- P968
wikidata_labels:
cs: Národní památkový ústav, knihovna
en: National Institute for the Protection and Conservation of Monuments and Sites, Directorate General, Library
wikidata_label_en: National Institute for the Protection and Conservation of Monuments and Sites, Directorate General, Library
wikidata_descriptions:
cs: knihovna v Praze
wikidata_aliases:
cs:
- Knihovna NPÚ - GnŘ
wikidata_classification:
instance_of: &id004
- id: Q385994
label: special library
description: specialized library providing resources on a particular topic or discipline
wikidata_instance_of: *id004
wikidata_location:
country: &id005
id: Q213
label: Czech Republic
description: country in Central Europe
headquarters_location:
id: Q748211
label: Old Town
description: neighborhood of Prague, Czech Republic
wikidata_country: *id005
wikidata_contact:
email: mailto:gnr.knihovna@npu.cz
_provenance:
content_hash:
algorithm: sha256
value: sha256-WkZ1IVzH+6U6fO70CHXOu3KC0YYXK4oJctvQefhzYxo=
scope: enrichment_section
computed_at: '2025-12-28T19:58:20.609644+00:00'
prov:
wasGeneratedBy:
'@type': prov:Activity
name: wikidata_api_fetch
used: https://www.wikidata.org/w/rest.php/wikibase/v1
wasDerivedFrom: https://www.wikidata.org/wiki/Q114617788
verification:
status: verified
last_verified: '2025-12-28T19:58:20.609655+00:00'
google_maps_status: NO_MATCH
google_maps_rejected:
candidate_name: National Heritage Institute
rejection_reason: The names match (Národní památkový ústav is the Czech name for National Heritage Institute) and the location in Brno, CZ, is correct. The website (npu.cz) also confirms the match. However, the Google Place types ('government_office', 'point_of_interest', 'establishment') do not match the expected heritage custodian types (museum, library, gallery, archive). The institution is a heritage management organization, not a public-facing heritage institution like a museum. Therefore, it does not fit the GRP.HER entity type definition.
timestamp: '2025-12-08T19:44:49.319194+00:00'
youtube_status: NOT_FOUND
youtube_search_query: Národní památkový ústav Brno official
youtube_search_timestamp: '2025-12-08T19:44:49.647135+00:00'
location:
latitude: 49.19522
longitude: 16.60796
coordinate_provenance:
source_type: GHCID_RESOLUTION_DIRECT
source_path: ghcid.location_resolution
original_timestamp: '2025-12-07T00:20:05.271885+00:00'
entity_id: 3078610
resolution_method: CH_ANNOTATOR_TOP_SET
city: Brno
region: CZ-10
region_code: '10'
country: CZ
geonames_id: 3078610
feature_code: PPLA
normalization_timestamp: '2025-12-09T06:49:27.314863+00:00'