glam/data/custodian.backup.20251230/CZ-20-BEN-A-SOAB.yaml
2025-12-30 23:19:38 +01:00

272 lines
9.1 KiB
YAML

original_entry:
name: Státní okresní archiv Benešov
institution_type: ARCHIVE
source: CH-Annotator (czech_unified_ch_annotator.yaml)
identifiers:
- &id001
identifier_scheme: ARON_UUID
identifier_value: 37895717-3b25-44b1-b9d4-e4c75a719fc6
identifier_url: https://portal.nacr.cz/aron/apu/37895717-3b25-44b1-b9d4-e4c75a719fc6
- &id002
identifier_scheme: INSTITUTION_CODE
identifier_value: '221201010'
- &id003
identifier_scheme: Wikidata
identifier_value: Q53779368
identifier_url: https://www.wikidata.org/wiki/Q53779368
- &id004
identifier_scheme: VIAF
identifier_value: '143385978'
identifier_url: https://viaf.org/viaf/143385978
locations: []
processing_timestamp: '2025-12-06T23:37:44.009637+00:00'
ghcid:
ghcid_current: CZ-20-BEN-A-SOAB
ghcid_original: XX-XX-XXX-A-SOAB
ghcid_uuid: ccdeec42-0a3d-5d7a-bf58-313cfd560638
ghcid_uuid_sha256: f0949693-4ab2-8d4b-ec3e-529961feec39
ghcid_numeric: 17335646425013431627
record_id: a0be2cc7-63bf-46bc-85bf-70fcc1454cf8
generation_timestamp: '2025-12-06T23:37:44.009637+00:00'
location_resolution:
country_code: CZ
region_code: '20'
city_code: BEN
method: CH_ANNOTATOR_TOP_SET
resolution_timestamp: '2025-12-07T00:19:32.989573+00:00'
region_name: CZ-20
iso_code_source: CZ-20
city_name: Benesov
geonames_id: 3079508
feature_code: PPL
extracted_toponym: Benešov
latitude: 49.78162
longitude: 14.68697
ghcid_history:
- ghcid: XX-XX-XXX-A-SOAB
ghcid_numeric: 17335646425013431627
valid_from: '2025-12-06T23:37:44.009637+00:00'
reason: Initial GHCID from CH-Annotator (czech_unified_ch_annotator.yaml)
- ghcid: CZ-XX-XXX-A-SOAB
valid_from: '2025-12-06T23:54:38.614560+00:00'
reason: 'Country resolved via Wikidata P17: XX→CZ'
- ghcid: CZ-20-XXX-A-SOAB
valid_from: '2025-12-07T00:04:24.694278+00:00'
reason: 'Region resolved via Wikidata P131: XX->20 (CZ-20)'
- ghcid: CZ-20-BEN-A-SOAB
valid_from: '2025-12-07T00:19:32.989579+00:00'
reason: 'Location resolved via CH-Annotator TOP.SET extraction: Benešov -> Benesov (GeoNames:3079508)'
custodian_name:
claim_type: custodian_name
claim_value: Státní okresní archiv Benešov
source_type: ch_annotator
identifiers:
- identifier_scheme: GHCID
identifier_value: XX-XX-XXX-A-SOAB
- identifier_scheme: GHCID_UUID
identifier_value: ccdeec42-0a3d-5d7a-bf58-313cfd560638
- identifier_scheme: GHCID_UUID_SHA256
identifier_value: f0949693-4ab2-8d4b-ec3e-529961feec39
- identifier_scheme: GHCID_NUMERIC
identifier_value: '17335646425013431627'
- identifier_scheme: RECORD_ID
identifier_value: a0be2cc7-63bf-46bc-85bf-70fcc1454cf8
- *id001
- *id002
- *id003
- *id004
provenance:
data_source: API_SCRAPING
data_tier: TIER_1_AUTHORITATIVE
extraction_date: '2025-11-19T11:35:45.743885+00:00'
extraction_method: 'Created from CH-Annotator file: czech_unified_ch_annotator.yaml'
confidence_score: 0.85
notes:
- 'Country resolved 2025-12-06T23:54:38Z: XX→CZ via Wikidata P17'
- 'Region resolved 2025-12-07T00:04:24Z: XX->20 via Wikidata P131 (CZ-20)'
- 'Location resolved 2025-12-07T00:19:32Z: CH-Annotator TOP.SET extraction ''Benešov'' -> Benesov (GeoNames:3079508, Region:72)'
- Canonical location added via normalize_custodian_files.py on 2025-12-08T23:48:08Z
- Canonical location added via normalize_custodian_files.py on 2025-12-09T06:49:31Z
- 'YouTube/Google Maps enrichment 2025-12-09T09:29:40Z: YouTube: not found'
schema_version: 2.0.0
enrichment_provenance:
wikidata_enrichment:
content_hash: sha256-f5P1MMexg3VNCcsZ6MU/Udw1eCnI+4/W6ZDTcZ9OCnw=
verified_at: '2025-12-28T19:58:35.430273+00:00'
wasDerivedFrom: https://www.wikidata.org/wiki/Q53779368
provenance_schema_version: '2.0'
standards_compliance:
- W3C PROV-O
- W3C SRI (content hashes)
generated_at: '2025-12-28T19:58:35.430296+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: '2025-11-19T11:35:45.743885+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: Státní okresní archiv Benešov
property_uri: skos:prefLabel
provenance:
namespace: glam
path: /files/czech_unified.yaml
timestamp: '2025-11-19T11:35:45.743885+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: '2025-11-19T11:35:45.743885+00:00'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
confidence: 0.95
- claim_type: wikidata_id
claim_value: Q53779368
property_uri: owl:sameAs
provenance:
namespace: wikidata
path: /entity/Q53779368
timestamp: '2025-11-19T11:35:45.743885+00:00'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
confidence: 0.98
- claim_type: location_settlement
claim_value: Benesov
property_uri: schema:location
hypernym_code: TOP.SET
hypernym_label: SETTLEMENT
provenance:
namespace: geonames
path: /geonames/3079508
timestamp: '2025-12-07T00:19:32.989582+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: Benešov
method: pattern_matching
integration_note:
created_from: czech_unified_ch_annotator.yaml
creation_date: '2025-12-06T23:37:44.009637+00:00'
creation_method: create_custodian_from_ch_annotator.py
wikidata_enrichment:
wikidata_entity_id: Q53779368
api_metadata:
api_endpoint: https://www.wikidata.org/w/rest.php/wikibase/v1
fetch_timestamp: '2025-12-08T23:41:53.093611+00:00'
user_agent: GLAMDataExtractor/1.1 (glam-data@example.com) Python/httpx
enrichment_version: 2.0_full
properties_found:
- P31
- P17
- P214
- P159
- P244
- P361
- P18
- P373
- P856
wikidata_labels:
cs: Státní okresní archiv Benešov
en: Státní okresní archiv Benešov
wikidata_label_en: Státní okresní archiv Benešov
wikidata_descriptions:
cs: archiv v Benešově
wikidata_aliases:
cs:
- SOkA Benešov
wikidata_sitelinks:
cswiki: Státní okresní archiv Benešov
commonswiki: Category:Státní okresní archiv Benešov
wikidata_classification:
instance_of: &id005
- id: Q53131316
label: state district archive
description: Archive type in the Czech Republic
wikidata_instance_of: *id005
wikidata_location:
country: &id006
id: Q213
label: Czech Republic
description: country in Central Europe
headquarters_location:
id: Q470394
label: Benešov
description: town in Czechia
wikidata_country: *id006
wikidata_organization:
part_of:
id: Q12056840
label: State Regional Archives in Prague
description: Czech archive
wikidata_web:
official_website: https://www.soapraha.cz/benesov/
wikidata_official_website: https://www.soapraha.cz/benesov/
wikidata_media:
image: SOkA Benešov headquarters.jpg
commons_category: Státní okresní archiv Benešov
wikidata_image: SOkA Benešov headquarters.jpg
_provenance:
content_hash:
algorithm: sha256
value: sha256-f5P1MMexg3VNCcsZ6MU/Udw1eCnI+4/W6ZDTcZ9OCnw=
scope: enrichment_section
computed_at: '2025-12-28T19:58:35.430273+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/Q53779368
verification:
status: verified
last_verified: '2025-12-28T19:58:35.430285+00:00'
location:
latitude: 49.78162
longitude: 14.68697
coordinate_provenance:
source_type: GHCID_RESOLUTION_DIRECT
source_path: ghcid.location_resolution
original_timestamp: '2025-12-07T00:19:32.989573+00:00'
entity_id: 3079508
resolution_method: CH_ANNOTATOR_TOP_SET
city: Benesov
region: CZ-20
region_code: '20'
country: CZ
geonames_id: 3079508
feature_code: PPL
normalization_timestamp: '2025-12-09T06:49:31.855564+00:00'
youtube_status: NOT_FOUND
youtube_search_query: Státní okresní archiv Benešov official
youtube_search_timestamp: '2025-12-09T09:29:40.790718+00:00'