314 lines
11 KiB
YAML
314 lines
11 KiB
YAML
original_entry:
|
|
name: Státní okresní archiv České Budějovice
|
|
institution_type: ARCHIVE
|
|
source: CH-Annotator (czech_unified_ch_annotator.yaml)
|
|
identifiers:
|
|
- &id001
|
|
identifier_scheme: ARON_UUID
|
|
identifier_value: db4fe44a-4f09-47cb-ab92-580c25d3c2d2
|
|
identifier_url: https://portal.nacr.cz/aron/apu/db4fe44a-4f09-47cb-ab92-580c25d3c2d2
|
|
- &id002
|
|
identifier_scheme: INSTITUTION_CODE
|
|
identifier_value: '222101010'
|
|
- &id003
|
|
identifier_scheme: Wikidata
|
|
identifier_value: Q54763949
|
|
identifier_url: https://www.wikidata.org/wiki/Q54763949
|
|
- &id004
|
|
identifier_scheme: VIAF
|
|
identifier_value: '149940850'
|
|
identifier_url: https://viaf.org/viaf/149940850
|
|
locations: []
|
|
processing_timestamp: '2025-12-06T23:37:44.763536+00:00'
|
|
ghcid:
|
|
ghcid_current: CZ-31-CES-A-SOACB
|
|
ghcid_original: XX-XX-XXX-A-SOAČB
|
|
ghcid_uuid: 601e9039-1567-58cf-a1df-c6accc719ad7
|
|
ghcid_uuid_sha256: 3c7ffc91-d6f9-8769-af4b-868f5da02f03
|
|
ghcid_numeric: 4359480667625043817
|
|
record_id: 9f89f85d-2ea9-4fcb-a308-2a38c50bf833
|
|
generation_timestamp: '2025-12-06T23:37:44.763536+00:00'
|
|
location_resolution:
|
|
country_code: CZ
|
|
region_code: '31'
|
|
city_code: CES
|
|
method: CH_ANNOTATOR_TOP_SET
|
|
resolution_timestamp: '2025-12-07T00:19:31.869773+00:00'
|
|
city_name: Ceske Budejovice
|
|
geonames_id: 3077916
|
|
feature_code: PPLA
|
|
extracted_toponym: České
|
|
latitude: 48.97447
|
|
longitude: 14.47434
|
|
ghcid_history:
|
|
- previous_ghcid_component: CB
|
|
new_ghcid_component: CES
|
|
change_date: '2025-12-20T19:55:24Z'
|
|
reason: 'Fixed 2-letter city code to proper 3-letter code per AGENTS.md. City: Ceske Budejovice'
|
|
- ghcid: CZ-31-CB-A-SOACB
|
|
ghcid_numeric: 4359480667625043817
|
|
valid_from: '2025-12-08T11:21:41.140930+00:00'
|
|
reason: 'Normalized diacritics to ASCII per ABBREV-DIACRITICS rule (was: CZ-31-CB-A-SOAČB)'
|
|
- ghcid: XX-XX-XXX-A-SOAČB
|
|
ghcid_numeric: 16282507436823768450
|
|
valid_from: '2025-12-06T23:37:44.763536+00:00'
|
|
reason: Initial GHCID from CH-Annotator (czech_unified_ch_annotator.yaml)
|
|
valid_to: '2025-12-08T11:21:41.140930+00:00'
|
|
- ghcid: CZ-XX-XXX-A-SOAČB
|
|
valid_from: '2025-12-06T23:54:39.389462+00:00'
|
|
reason: 'Country resolved via Wikidata P17: XX→CZ'
|
|
- ghcid: CZ-31-CB-A-SOAČB
|
|
valid_from: '2025-12-07T00:19:31.869780+00:00'
|
|
reason: 'Location resolved via CH-Annotator TOP.SET extraction: České -> Ceske Budejovice (GeoNames:3077916)'
|
|
custodian_name:
|
|
claim_type: custodian_name
|
|
claim_value: Státní okresní archiv České Budějovice
|
|
source_type: ch_annotator
|
|
identifiers:
|
|
- identifier_scheme: GHCID
|
|
identifier_value: CZ-31-CB-A-SOACB
|
|
- identifier_scheme: GHCID_UUID
|
|
identifier_value: 601e9039-1567-58cf-a1df-c6accc719ad7
|
|
- identifier_scheme: GHCID_UUID_SHA256
|
|
identifier_value: 3c7ffc91-d6f9-8769-af4b-868f5da02f03
|
|
- identifier_scheme: GHCID_NUMERIC
|
|
identifier_value: '4359480667625043817'
|
|
- identifier_scheme: RECORD_ID
|
|
identifier_value: 9f89f85d-2ea9-4fcb-a308-2a38c50bf833
|
|
- *id001
|
|
- *id002
|
|
- *id003
|
|
- *id004
|
|
provenance:
|
|
data_source: API_SCRAPING
|
|
data_tier: TIER_1_AUTHORITATIVE
|
|
extraction_date: '2025-11-19T11:35:45.745373+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'
|
|
- 'Location resolved 2025-12-07T00:19:31Z: CH-Annotator TOP.SET extraction ''České'' -> Ceske Budejovice (GeoNames:3077916, Region:31)'
|
|
- Canonical location added via normalize_custodian_files.py on 2025-12-08T23:48:09Z
|
|
- Canonical location added via normalize_custodian_files.py on 2025-12-09T06:49:33Z
|
|
- 'YouTube/Google Maps enrichment 2025-12-09T09:30:11Z: YouTube: not found'
|
|
schema_version: 2.0.0
|
|
enrichment_provenance:
|
|
wikidata_enrichment:
|
|
content_hash: sha256-TQ7BnMdkgf23SnKBik99a9XGd78/Odmt/Q5GRUirZM0=
|
|
verified_at: '2025-12-28T19:58:49.973828+00:00'
|
|
wasDerivedFrom: https://www.wikidata.org/wiki/Q54763949
|
|
provenance_schema_version: '2.0'
|
|
standards_compliance:
|
|
- W3C PROV-O
|
|
- W3C SRI (content hashes)
|
|
generated_at: '2025-12-28T19:58:49.973848+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: '2025-11-19T11:35:45.745373+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 České Budějovice
|
|
property_uri: skos:prefLabel
|
|
provenance:
|
|
namespace: glam
|
|
path: /files/czech_unified.yaml
|
|
timestamp: '2025-11-19T11:35:45.745373+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: '2025-11-19T11:35:45.745373+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 0.95
|
|
- claim_type: wikidata_id
|
|
claim_value: Q54763949
|
|
property_uri: owl:sameAs
|
|
provenance:
|
|
namespace: wikidata
|
|
path: /entity/Q54763949
|
|
timestamp: '2025-11-19T11:35:45.745373+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 0.98
|
|
- claim_type: location_settlement
|
|
claim_value: Ceske Budejovice
|
|
property_uri: schema:location
|
|
hypernym_code: TOP.SET
|
|
hypernym_label: SETTLEMENT
|
|
provenance:
|
|
namespace: geonames
|
|
path: /geonames/3077916
|
|
timestamp: '2025-12-07T00:19:31.869783+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: České
|
|
method: pattern_matching
|
|
integration_note:
|
|
created_from: czech_unified_ch_annotator.yaml
|
|
creation_date: '2025-12-06T23:37:44.763536+00:00'
|
|
creation_method: create_custodian_from_ch_annotator.py
|
|
wikidata_enrichment:
|
|
wikidata_entity_id: Q54763949
|
|
api_metadata:
|
|
api_endpoint: https://www.wikidata.org/w/rest.php/wikibase/v1
|
|
fetch_timestamp: '2025-12-08T23:42:43.019534+00:00'
|
|
user_agent: GLAMDataExtractor/1.1 (glam-data@example.com) Python/httpx
|
|
enrichment_version: 2.0_full
|
|
properties_found:
|
|
- P31
|
|
- P17
|
|
- P625
|
|
- P214
|
|
- P361
|
|
- P856
|
|
- P131
|
|
- P18
|
|
- P373
|
|
wikidata_labels:
|
|
cs: Státní okresní archiv České Budějovice
|
|
en: State Disctrict Archives České Budějovice
|
|
wikidata_label_en: State Disctrict Archives České Budějovice
|
|
wikidata_descriptions:
|
|
cs: archiv v Českých Budějovicích
|
|
en: organization in České Budějovice, Czechia
|
|
wikidata_description_en: organization in České Budějovice, Czechia
|
|
wikidata_aliases:
|
|
cs:
|
|
- SOkA České Budějovice
|
|
wikidata_sitelinks:
|
|
commonswiki: Category:Státní okresní archiv České Budějovice
|
|
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
|
|
coordinates: &id008
|
|
latitude: 48.9759786
|
|
longitude: 14.4849425
|
|
precision: 1.0e-07
|
|
located_in_admin_entity: &id007
|
|
id: Q16506
|
|
label: České Budějovice
|
|
description: city in Czechia
|
|
wikidata_country: *id006
|
|
wikidata_located_in: *id007
|
|
wikidata_coordinates: *id008
|
|
wikidata_organization:
|
|
part_of:
|
|
id: Q12056841
|
|
label: Regional State Archives in Třeboň
|
|
description: archives in the Czech Republic
|
|
wikidata_web:
|
|
official_website: http://www.ceskearchivy.cz/statni-okresni-archivy/ceske-budejovice
|
|
wikidata_official_website: http://www.ceskearchivy.cz/statni-okresni-archivy/ceske-budejovice
|
|
wikidata_media:
|
|
image: State Regional Archive České Budějovice 02.jpg
|
|
commons_category: Státní okresní archiv České Budějovice
|
|
wikidata_image: State Regional Archive České Budějovice 02.jpg
|
|
_provenance:
|
|
content_hash:
|
|
algorithm: sha256
|
|
value: sha256-TQ7BnMdkgf23SnKBik99a9XGd78/Odmt/Q5GRUirZM0=
|
|
scope: enrichment_section
|
|
computed_at: '2025-12-28T19:58:49.973828+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/Q54763949
|
|
verification:
|
|
status: verified
|
|
last_verified: '2025-12-28T19:58:49.973838+00:00'
|
|
location:
|
|
latitude: 48.9759786
|
|
longitude: 14.4849425
|
|
coordinate_provenance:
|
|
source_type: WIKIDATA
|
|
source_path: wikidata_enrichment.wikidata_coordinates
|
|
original_timestamp: '2025-12-08T23:42:43.019534+00:00'
|
|
api_endpoint: https://www.wikidata.org/w/rest.php/wikibase/v1
|
|
entity_id: Q54763949
|
|
city: Ceske Budejovice
|
|
region_code: '31'
|
|
country: CZ
|
|
geonames_id: 3077916
|
|
feature_code: PPLA
|
|
normalization_timestamp: '2025-12-09T06:49:33.052451+00:00'
|
|
youtube_status: NOT_FOUND
|
|
youtube_search_query: Státní okresní archiv České Budějovice official
|
|
youtube_search_timestamp: '2025-12-09T09:30:11.436895+00:00'
|
|
logo_enrichment:
|
|
enrichment_timestamp: '2025-12-24T01:36:42.026349+00:00'
|
|
source_url: http://www.ceskearchivy.cz/statni-okresni-archivy/ceske-budejovice
|
|
extraction_method: crawl4ai
|
|
claims:
|
|
- claim_type: logo_url
|
|
claim_value: http://www.ceskearchivy.cz/images/INST_logo.png
|
|
source_url: http://www.ceskearchivy.cz/statni-okresni-archivy/ceske-budejovice
|
|
css_selector: '#mod-custom206 > p > a > img'
|
|
retrieved_on: '2025-12-24T01:36:42.026349+00:00'
|
|
extraction_method: crawl4ai_header_logo
|
|
detection_confidence: high
|
|
alt_text: ''
|
|
- claim_type: favicon_url
|
|
claim_value: http://www.ceskearchivy.cz/favicon.ico
|
|
source_url: http://www.ceskearchivy.cz/statni-okresni-archivy/ceske-budejovice
|
|
css_selector: '[document] > html > head > link:nth-of-type(3)'
|
|
retrieved_on: '2025-12-24T01:36:42.026349+00:00'
|
|
extraction_method: crawl4ai_link_rel
|
|
favicon_type: image/vnd.microsoft.icon
|
|
favicon_sizes: ''
|
|
- claim_type: og_image_url
|
|
claim_value: http://www.ceskearchivy.cz/administrator/cache/preview/80b931d60f4be56fcd0c341aab8b9bc2.jpg
|
|
source_url: http://www.ceskearchivy.cz/statni-okresni-archivy/ceske-budejovice
|
|
css_selector: '[document] > html > head > meta:nth-of-type(7)'
|
|
retrieved_on: '2025-12-24T01:36:42.026349+00:00'
|
|
extraction_method: crawl4ai_meta_og
|
|
summary:
|
|
total_claims: 3
|
|
has_primary_logo: true
|
|
has_favicon: true
|
|
has_og_image: true
|
|
favicon_count: 1
|