198 lines
6.8 KiB
YAML
198 lines
6.8 KiB
YAML
original_entry:
|
|
name: Státní oblastní archiv v Třeboni - oddělení České Budějovice
|
|
institution_type: OFFICIAL_INSTITUTION
|
|
source: CH-Annotator (czech_unified_ch_annotator.yaml)
|
|
identifiers:
|
|
- &id001
|
|
identifier_scheme: Sigla
|
|
identifier_value: CBE009
|
|
- &id002
|
|
identifier_scheme: IČO
|
|
identifier_value: '70978956'
|
|
- &id003
|
|
identifier_scheme: Website
|
|
identifier_value: https://www.ceskearchivy.cz/
|
|
identifier_url: https://www.ceskearchivy.cz/
|
|
locations:
|
|
- street_address: Rudolfovská 40
|
|
postal_code: 370 01
|
|
city: České Budějovice
|
|
region: Jihočeský
|
|
country: CZ
|
|
latitude: 48.976414
|
|
longitude: 14.484597
|
|
processing_timestamp: '2025-12-06T23:37:43.588196+00:00'
|
|
ghcid:
|
|
ghcid_current: CZ-64-CES-O-SOAVTOCB
|
|
ghcid_original: CZ-JI-CES-O-SOAVTOČB
|
|
ghcid_uuid: 940b880a-4cf6-5868-bbc7-d901bae901ef
|
|
ghcid_uuid_sha256: a155644f-2fbf-8801-a094-6496b7fc8a34
|
|
ghcid_numeric: 11625308304393082881
|
|
record_id: 0f11061c-ae8c-4420-8a6c-8af88f6bb6b4
|
|
generation_timestamp: '2025-12-06T23:37:43.588196+00:00'
|
|
location_resolution:
|
|
country_code: CZ
|
|
region_code: 64
|
|
city_code: CES
|
|
method: CH_ANNOTATOR_SOURCE
|
|
ghcid_history:
|
|
- ghcid: CZ-64-CES-O-SOAVTOCB
|
|
valid_from: '2025-12-10T09:47:00Z'
|
|
valid_to: null
|
|
reason: Corrected region code from CZ-JI to CZ-64 (South Moravian (Jihomoravský))
|
|
per ISO 3166-2:CZ
|
|
- ghcid: CZ-JI-CES-O-SOAVTOCB
|
|
valid_from: null
|
|
valid_to: '2025-12-10T09:47:00Z'
|
|
reason: Previous GHCID with incorrect region code
|
|
- ghcid: CZ-JI-CES-O-SOAVTOCB
|
|
ghcid_numeric: 11625308304393082881
|
|
valid_from: '2025-12-08T11:21:30.893530+00:00'
|
|
reason: 'Normalized diacritics to ASCII per ABBREV-DIACRITICS rule (was: CZ-JI-CES-O-SOAVTOČB)'
|
|
- ghcid: CZ-JI-CES-O-SOAVTOČB
|
|
ghcid_numeric: 9208888999552746134
|
|
valid_from: '2025-12-06T23:37:43.588196+00:00'
|
|
reason: Initial GHCID from CH-Annotator (czech_unified_ch_annotator.yaml)
|
|
valid_to: '2025-12-08T11:21:30.893530+00:00'
|
|
custodian_name:
|
|
claim_type: custodian_name
|
|
claim_value: Státní oblastní archiv v Třeboni - oddělení České Budějovice
|
|
source_type: ch_annotator
|
|
identifiers:
|
|
- identifier_scheme: GHCID
|
|
identifier_value: CZ-64-CES-O-SOAVTOCB
|
|
- identifier_scheme: GHCID_UUID
|
|
identifier_value: 940b880a-4cf6-5868-bbc7-d901bae901ef
|
|
- identifier_scheme: GHCID_UUID_SHA256
|
|
identifier_value: a155644f-2fbf-8801-a094-6496b7fc8a34
|
|
- identifier_scheme: GHCID_NUMERIC
|
|
identifier_value: '11625308304393082881'
|
|
- identifier_scheme: RECORD_ID
|
|
identifier_value: 0f11061c-ae8c-4420-8a6c-8af88f6bb6b4
|
|
- *id001
|
|
- *id002
|
|
- *id003
|
|
provenance:
|
|
data_source: API_SCRAPING
|
|
data_tier: TIER_1_AUTHORITATIVE
|
|
extraction_date: '2025-11-19T10:14:30.309077+00:00'
|
|
extraction_method: 'Created from CH-Annotator file: czech_unified_ch_annotator.yaml'
|
|
confidence_score: 0.95
|
|
notes:
|
|
- Canonical location added via normalize_custodian_files.py on 2025-12-08T23:11:56Z
|
|
- Canonical location added via normalize_custodian_files.py on 2025-12-08T23:49:34Z
|
|
- Canonical location added via normalize_custodian_files.py on 2025-12-09T06:51:11Z
|
|
ch_annotator:
|
|
convention_id: ch_annotator-v1_7_0
|
|
convention_version: 1.7.0
|
|
entity_classification:
|
|
hypernym: GRP
|
|
hypernym_label: GROUP
|
|
subtype: GRP.HER.OFF
|
|
subtype_label: OFFICIAL_INSTITUTION
|
|
ontology_class: schema:GovernmentOrganization
|
|
alternative_classes:
|
|
- org:FormalOrganization
|
|
- rov:RegisteredOrganization
|
|
- glam:HeritageCustodian
|
|
extraction_provenance:
|
|
namespace: glam
|
|
path: /files/czech_unified.yaml
|
|
timestamp: '2025-11-19T10:14:30.309077+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: 0.95
|
|
verified: false
|
|
verification_date: null
|
|
verified_by: null
|
|
entity_claims:
|
|
- claim_type: full_name
|
|
claim_value: Státní oblastní archiv v Třeboni - oddělení České Budějovice
|
|
property_uri: skos:prefLabel
|
|
provenance:
|
|
namespace: glam
|
|
path: /files/czech_unified.yaml
|
|
timestamp: '2025-11-19T10:14:30.309077+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 0.95
|
|
- claim_type: institution_type
|
|
claim_value: OFFICIAL_INSTITUTION
|
|
property_uri: rdf:type
|
|
provenance:
|
|
namespace: glam
|
|
path: /files/czech_unified.yaml
|
|
timestamp: '2025-11-19T10:14:30.309077+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 0.95
|
|
- claim_type: located_in_city
|
|
claim_value: České Budějovice
|
|
property_uri: schema:addressLocality
|
|
provenance:
|
|
namespace: glam
|
|
path: /files/czech_unified.yaml
|
|
timestamp: '2025-11-19T10:14:30.309077+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 0.9
|
|
- claim_type: ghcid
|
|
claim_value: CZ-CBE009
|
|
property_uri: glam:ghcid
|
|
provenance:
|
|
namespace: glam
|
|
path: /files/czech_unified.yaml
|
|
timestamp: '2025-11-19T10:14:30.309077+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 1.0
|
|
integration_note:
|
|
created_from: czech_unified_ch_annotator.yaml
|
|
creation_date: '2025-12-06T23:37:43.588196+00:00'
|
|
creation_method: create_custodian_from_ch_annotator.py
|
|
location:
|
|
latitude: 48.976414
|
|
longitude: 14.484597
|
|
coordinate_provenance:
|
|
source_type: ORIGINAL_ENTRY
|
|
source_path: original_entry.locations[0]
|
|
city: České Budějovice
|
|
region: Jihočeský
|
|
region_code: 64
|
|
country: CZ
|
|
postal_code: 370 01
|
|
street_address: Rudolfovská 40
|
|
normalization_timestamp: '2025-12-09T06:51:11.303011+00:00'
|
|
logo_enrichment:
|
|
enrichment_timestamp: '2025-12-27T19:11:11.576239+00:00'
|
|
source_url: https://www.ceskearchivy.cz
|
|
extraction_method: crawl4ai
|
|
claims:
|
|
- claim_type: logo_url
|
|
claim_value: https://www.ceskearchivy.cz/images/INST_logo.png
|
|
source_url: https://www.ceskearchivy.cz
|
|
css_selector: '#mod-custom206 > p > a > img'
|
|
retrieved_on: '2025-12-27T19:11:11.576239+00:00'
|
|
extraction_method: crawl4ai_header_logo
|
|
detection_confidence: high
|
|
alt_text: ''
|
|
- claim_type: favicon_url
|
|
claim_value: https://www.ceskearchivy.cz/favicon.ico
|
|
source_url: https://www.ceskearchivy.cz
|
|
css_selector: '[document] > html > head > link:nth-of-type(3)'
|
|
retrieved_on: '2025-12-27T19:11:11.576239+00:00'
|
|
extraction_method: crawl4ai_link_rel
|
|
favicon_type: image/vnd.microsoft.icon
|
|
favicon_sizes: ''
|
|
summary:
|
|
total_claims: 2
|
|
has_primary_logo: true
|
|
has_favicon: true
|
|
has_og_image: false
|
|
favicon_count: 1
|