glam/data/custodian.backup.20251230/CZ-71-KLA-A-SOAK-statni_okresni_archiv_klatovy.yaml
2025-12-30 23:19:38 +01:00

275 lines
9.3 KiB
YAML

custodian_name:
claim_type: custodian_name
claim_value: Státní okresní archiv Klatovy
source_type: ch_annotator
original_entry:
name: Státní okresní archiv Klatovy
institution_type: ARCHIVE
source: CH-Annotator (czech_unified_ch_annotator.yaml)
identifiers:
- &id001
identifier_scheme: ARON_UUID
identifier_value: f47ec156-a6bf-4247-a3c7-220427a2a34e
identifier_url: https://portal.nacr.cz/aron/apu/f47ec156-a6bf-4247-a3c7-220427a2a34e
- &id002
identifier_scheme: INSTITUTION_CODE
identifier_value: '223102010'
- &id003
identifier_scheme: Wikidata
identifier_value: Q54009981
identifier_url: https://www.wikidata.org/wiki/Q54009981
- &id004
identifier_scheme: VIAF
identifier_value: '251040608'
identifier_url: https://viaf.org/viaf/251040608
locations: []
processing_timestamp: '2025-12-06T23:37:44.881791+00:00'
ghcid:
ghcid_current: CZ-71-KLA-A-SOAK-statni_okresni_archiv_klatovy
ghcid_original: XX-XX-XXX-A-SOAK-statni_okresni_archiv_klatovy
ghcid_uuid: 6a5adcc1-d53a-57e8-b699-fdb8ad8b71bd
ghcid_uuid_sha256: ff678f0f-326f-8f10-15d1-94e93ee04b89
ghcid_numeric: 18403835697706299152
record_id: 0789728c-fa1d-46d3-a625-712a278f05fe
generation_timestamp: '2025-12-06T23:37:44.881791+00:00'
location_resolution:
country_code: CZ
region_code: '71'
city_code: KLA
method: CH_ANNOTATOR_TOP_SET
resolution_timestamp: '2025-12-07T00:19:31.424971+00:00'
city_name: Klatovy
geonames_id: 3073660
feature_code: PPL
extracted_toponym: Klatovy
latitude: 49.39552
longitude: 13.29505
ghcid_history:
- ghcid: XX-XX-XXX-A-SOAK-statni_okresni_archiv_klatovy
ghcid_numeric: 18403835697706299152
valid_from: '2025-12-06T23:37:44.881791+00:00'
reason: Initial GHCID from CH-Annotator (czech_unified_ch_annotator.yaml)
- ghcid: CZ-XX-XXX-A-SOAK-statni_okresni_archiv_klatovy
valid_from: '2025-12-06T23:54:40.146840+00:00'
reason: 'Country resolved via Wikidata P17: XX→CZ'
- ghcid: CZ-71-KLA-A-SOAK-statni_okresni_archiv_klatovy
valid_from: '2025-12-07T00:19:31.424979+00:00'
reason: 'Location resolved via CH-Annotator TOP.SET extraction: Klatovy -> Klatovy (GeoNames:3073660)'
identifiers:
- identifier_scheme: GHCID
identifier_value: XX-XX-XXX-A-SOAK-statni_okresni_archiv_klatovy
- identifier_scheme: GHCID_UUID
identifier_value: 6a5adcc1-d53a-57e8-b699-fdb8ad8b71bd
- identifier_scheme: GHCID_UUID_SHA256
identifier_value: ff678f0f-326f-8f10-15d1-94e93ee04b89
- identifier_scheme: GHCID_NUMERIC
identifier_value: '18403835697706299152'
- identifier_scheme: RECORD_ID
identifier_value: 0789728c-fa1d-46d3-a625-712a278f05fe
- *id001
- *id002
- *id003
- *id004
provenance:
data_source: API_SCRAPING
data_tier: TIER_1_AUTHORITATIVE
extraction_date: '2025-11-19T11:35:45.745617+00:00'
extraction_method: 'Created from CH-Annotator file: czech_unified_ch_annotator.yaml'
confidence_score: 0.85
notes:
- 'Country resolved 2025-12-06T23:54:40Z: XX→CZ via Wikidata P17'
- 'Location resolved 2025-12-07T00:19:31Z: CH-Annotator TOP.SET extraction ''Klatovy'' -> Klatovy (GeoNames:3073660, Region:71)'
- Canonical location added via normalize_custodian_files.py on 2025-12-09T06:49:50Z
- 'YouTube/Google Maps enrichment 2025-12-09T09:35:45Z: YouTube: not found'
schema_version: 2.0.0
enrichment_provenance:
wikidata_enrichment:
content_hash: sha256-QMnVFWZr0K3esNFStoHmlaSGnChG7asfqCQ4/mDcWys=
verified_at: '2025-12-28T20:00:04.107425+00:00'
wasDerivedFrom: https://www.wikidata.org/wiki/Q54009981
provenance_schema_version: '2.0'
standards_compliance:
- W3C PROV-O
- W3C SRI (content hashes)
generated_at: '2025-12-28T20:00:04.107442+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: '2025-11-19T11:35:45.745617+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 Klatovy
property_uri: skos:prefLabel
provenance:
namespace: glam
path: /files/czech_unified.yaml
timestamp: '2025-11-19T11:35:45.745617+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: '2025-11-19T11:35:45.745617+00:00'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
confidence: 0.95
- claim_type: wikidata_id
claim_value: Q54009981
property_uri: owl:sameAs
provenance:
namespace: wikidata
path: /entity/Q54009981
timestamp: '2025-11-19T11:35:45.745617+00:00'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
confidence: 0.98
- claim_type: location_settlement
claim_value: Klatovy
property_uri: schema:location
hypernym_code: TOP.SET
hypernym_label: SETTLEMENT
provenance:
namespace: geonames
path: /geonames/3073660
timestamp: '2025-12-07T00:19:31.424982+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: Klatovy
method: pattern_matching
integration_note:
created_from: czech_unified_ch_annotator.yaml
creation_date: '2025-12-06T23:37:44.881791+00:00'
creation_method: create_custodian_from_ch_annotator.py
wikidata_enrichment:
wikidata_entity_id: Q54009981
api_metadata:
api_endpoint: https://www.wikidata.org/w/rest.php/wikibase/v1
fetch_timestamp: '2025-12-08T23:48:24.140534+00:00'
user_agent: GLAMDataExtractor/1.1 (glam-data@example.com) Python/httpx
enrichment_version: 2.0_full
properties_found:
- P31
- P17
- P361
- P159
- P214
- P856
wikidata_labels:
cs: Státní okresní archiv Klatovy
en: State District Archives Klatovy
wikidata_label_en: State District Archives Klatovy
wikidata_descriptions:
cs: archiv v Klatovech
wikidata_aliases:
cs:
- SOkA Klatovy
wikidata_sitelinks:
cswiki: Státní okresní archiv Klatovy
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: Q602976
label: Klatovy
description: town in Czechia
wikidata_country: *id006
wikidata_organization:
part_of:
id: Q21953079
label: State Regional Archives in Pilsen
description: archive covering West Bohemia, Czechia
wikidata_web:
official_website: https://www.soaplzen.cz/soka-kt
wikidata_official_website: https://www.soaplzen.cz/soka-kt
_provenance:
content_hash:
algorithm: sha256
value: sha256-QMnVFWZr0K3esNFStoHmlaSGnChG7asfqCQ4/mDcWys=
scope: enrichment_section
computed_at: '2025-12-28T20:00:04.107425+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/Q54009981
verification:
status: verified
last_verified: '2025-12-28T20:00:04.107433+00:00'
location:
latitude: 49.39552
longitude: 13.29505
coordinate_provenance:
source_type: GHCID_RESOLUTION_DIRECT
source_path: ghcid.location_resolution
original_timestamp: '2025-12-07T00:19:31.424971+00:00'
entity_id: 3073660
resolution_method: CH_ANNOTATOR_TOP_SET
city: Klatovy
region_code: '71'
country: CZ
geonames_id: 3073660
feature_code: PPL
normalization_timestamp: '2025-12-09T06:49:50.655471+00:00'
youtube_status: NOT_FOUND
youtube_search_query: Státní okresní archiv Klatovy official
youtube_search_timestamp: '2025-12-09T09:35:45.677838+00:00'
logo_enrichment:
enrichment_timestamp: '2025-12-27T21:37:34.140833+00:00'
source_url: https://www.soaplzen.cz/soka-kt
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: https://www.soaplzen.cz/sites/default/files/easybreeze_favicon.ico
source_url: https://www.soaplzen.cz/soka-kt
css_selector: '[document] > html.js > head > link'
retrieved_on: '2025-12-27T21:37:34.140833+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: image/x-icon
favicon_sizes: ''
summary:
total_claims: 1
has_primary_logo: false
has_favicon: true
has_og_image: false
favicon_count: 1