327 lines
12 KiB
YAML
327 lines
12 KiB
YAML
custodian_name:
|
|
claim_type: custodian_name
|
|
claim_value: Masarykův ústav a Archiv Akademie věd České republiky v.v.i.
|
|
source_type: ch_annotator
|
|
original_entry:
|
|
name: Masarykův ústav a Archiv Akademie věd České republiky v.v.i.
|
|
institution_type: ARCHIVE
|
|
source: CH-Annotator (czech_unified_ch_annotator.yaml)
|
|
identifiers:
|
|
- &id001
|
|
identifier_scheme: ARON_UUID
|
|
identifier_value: fda96318-bbd8-44a6-a5fd-01975970150e
|
|
identifier_url: https://portal.nacr.cz/aron/apu/fda96318-bbd8-44a6-a5fd-01975970150e
|
|
- &id002
|
|
identifier_scheme: INSTITUTION_CODE
|
|
identifier_value: '610000070'
|
|
- &id003
|
|
identifier_scheme: Wikidata
|
|
identifier_value: Q26832919
|
|
identifier_url: https://www.wikidata.org/wiki/Q26832919
|
|
- &id004
|
|
identifier_scheme: VIAF
|
|
identifier_value: '108145857838223021029'
|
|
identifier_url: https://viaf.org/viaf/108145857838223021029
|
|
locations: []
|
|
processing_timestamp: '2025-12-06T23:37:44.936251+00:00'
|
|
ghcid:
|
|
ghcid_current: CZ-10-PET-A-MUAAVCRVV
|
|
ghcid_original: XX-XX-XXX-A-MÚAAVČRVV
|
|
ghcid_uuid: f61c0ccb-105e-5eb2-b443-8dfe2341cf94
|
|
ghcid_uuid_sha256: 1ce57b05-35f9-89c6-bbce-c59dd0871109
|
|
ghcid_numeric: 2082205665039325638
|
|
record_id: b871b584-6357-4db2-9718-4bd2d75bb7d8
|
|
generation_timestamp: '2025-12-06T23:37:44.936251+00:00'
|
|
location_resolution:
|
|
country_code: CZ
|
|
region_code: '10'
|
|
city_code: PET
|
|
method: WIKIDATA_COORDS_REVERSE_GEOCODE
|
|
resolution_timestamp: '2025-12-07T00:36:36.473342+00:00'
|
|
region_name: CZ-10
|
|
iso_code_source: CZ-10
|
|
city_label: Pelc Tyrolka
|
|
geonames_id: 3068455
|
|
ghcid_history:
|
|
- previous_ghcid_component: PT
|
|
new_ghcid_component: PET
|
|
change_date: '2025-12-20T19:55:24Z'
|
|
reason: 'Fixed 2-letter city code to proper 3-letter code per AGENTS.md. City: Pelc Tyrolka'
|
|
- ghcid: CZ-10-PT-A-MUAAVCRVV
|
|
ghcid_numeric: 2082205665039325638
|
|
valid_from: '2025-12-08T11:21:23.279169+00:00'
|
|
reason: 'Normalized diacritics to ASCII per ABBREV-DIACRITICS rule (was: CZ-10-PT-A-MÚAAVČRVV)'
|
|
- ghcid: XX-XX-XXX-A-MÚAAVČRVV
|
|
ghcid_numeric: 2282408233211190476
|
|
valid_from: '2025-12-06T23:37:44.936251+00:00'
|
|
reason: Initial GHCID from CH-Annotator (czech_unified_ch_annotator.yaml)
|
|
valid_to: '2025-12-08T11:21:23.279169+00:00'
|
|
- ghcid: CZ-XX-XXX-A-MÚAAVČRVV
|
|
valid_from: '2025-12-06T23:54:38.653602+00:00'
|
|
reason: 'Country resolved via Wikidata P17: XX→CZ'
|
|
- ghcid: CZ-10-XXX-A-MÚAAVČRVV
|
|
valid_from: '2025-12-07T00:03:56.204525+00:00'
|
|
reason: 'Region resolved via Wikidata P131: XX->10 (CZ-10)'
|
|
- ghcid: CZ-10-PT-A-MÚAAVČRVV
|
|
valid_from: '2025-12-07T00:36:36.473356+00:00'
|
|
reason: 'City resolved via Wikidata Q26832919 coordinates: XXX->PT (Pelc Tyrolka)'
|
|
identifiers:
|
|
- identifier_scheme: GHCID
|
|
identifier_value: CZ-10-PT-A-MUAAVCRVV
|
|
- identifier_scheme: GHCID_UUID
|
|
identifier_value: f61c0ccb-105e-5eb2-b443-8dfe2341cf94
|
|
- identifier_scheme: GHCID_UUID_SHA256
|
|
identifier_value: 1ce57b05-35f9-89c6-bbce-c59dd0871109
|
|
- identifier_scheme: GHCID_NUMERIC
|
|
identifier_value: '2082205665039325638'
|
|
- identifier_scheme: RECORD_ID
|
|
identifier_value: b871b584-6357-4db2-9718-4bd2d75bb7d8
|
|
- *id001
|
|
- *id002
|
|
- *id003
|
|
- *id004
|
|
provenance:
|
|
data_source: API_SCRAPING
|
|
data_tier: TIER_1_AUTHORITATIVE
|
|
extraction_date: '2025-11-19T11:35:45.745707+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 2025-12-07T00:03:56Z: XX->10 via Wikidata P131 (CZ-10)'
|
|
- 'City resolved 2025-12-07T00:36:36Z: XXX->PT via Wikidata Q26832919 coords (50.1184,14.4631) -> Pelc Tyrolka (GeoNames:3068455)'
|
|
- 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 2025-12-09T09:29:39Z: YouTube: not found'
|
|
schema_version: 2.0.0
|
|
enrichment_provenance:
|
|
wikidata_enrichment:
|
|
content_hash: sha256-pwa7gVAwrSuq+W6+LvRtp5x3xsm96AYqer68qrBBvG8=
|
|
verified_at: '2025-12-28T19:58:20.926216+00:00'
|
|
wasDerivedFrom: https://www.wikidata.org/wiki/Q26832919
|
|
provenance_schema_version: '2.0'
|
|
standards_compliance:
|
|
- W3C PROV-O
|
|
- W3C SRI (content hashes)
|
|
generated_at: '2025-12-28T19:58:20.926232+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: '2025-11-19T11:35:45.745707+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: Masarykův ústav a Archiv Akademie věd České republiky v.v.i.
|
|
property_uri: skos:prefLabel
|
|
provenance:
|
|
namespace: glam
|
|
path: /files/czech_unified.yaml
|
|
timestamp: '2025-11-19T11:35:45.745707+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: '2025-11-19T11:35:45.745707+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 0.95
|
|
- claim_type: wikidata_id
|
|
claim_value: Q26832919
|
|
property_uri: owl:sameAs
|
|
provenance:
|
|
namespace: wikidata
|
|
path: /entity/Q26832919
|
|
timestamp: '2025-11-19T11:35:45.745707+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 0.98
|
|
integration_note:
|
|
created_from: czech_unified_ch_annotator.yaml
|
|
creation_date: '2025-12-06T23:37:44.936251+00:00'
|
|
creation_method: create_custodian_from_ch_annotator.py
|
|
wikidata_enrichment:
|
|
wikidata_entity_id: Q26832919
|
|
api_metadata:
|
|
api_endpoint: https://www.wikidata.org/w/rest.php/wikibase/v1
|
|
fetch_timestamp: '2025-12-08T23:41:49.831054+00:00'
|
|
user_agent: GLAMDataExtractor/1.1 (glam-data@example.com) Python/httpx
|
|
enrichment_version: 2.0_full
|
|
properties_found:
|
|
- P214
|
|
- P227
|
|
- P31
|
|
- P361
|
|
- P17
|
|
- P856
|
|
- P2427
|
|
- P213
|
|
- P3500
|
|
- P625
|
|
- P131
|
|
- P18
|
|
- P749
|
|
- P154
|
|
- P373
|
|
- P6782
|
|
- P2013
|
|
- P1436
|
|
- P2671
|
|
wikidata_labels:
|
|
cs: Masarykův ústav a Archiv Akademie věd České republiky
|
|
en: Masaryk Institute and Archives
|
|
ca: Institut i Arxiu Masaryk
|
|
sl: Masarykov inštitut in arhiv
|
|
wikidata_label_en: Masaryk Institute and Archives
|
|
wikidata_descriptions:
|
|
en: archive of the Czech Academy of Sciences in Prague
|
|
cs: česká výzkumná organizace
|
|
ar: دار نشر
|
|
sl: arhiv Akademije znanosti Češke republike
|
|
wikidata_description_en: archive of the Czech Academy of Sciences in Prague
|
|
wikidata_aliases:
|
|
en:
|
|
- Masarykův ústav a Archiv AV ČR
|
|
- Masaryk Institute and Archives of the Czech Academy of Science
|
|
cs:
|
|
- Masarykův ústav a Archiv AV ČR, v. v. i.
|
|
sl:
|
|
- Masarykův ústav a Archiv Akademie věd České republiky
|
|
wikidata_sitelinks:
|
|
commonswiki: Category:Masaryk Institute and Archives of the Czech Academy of Sciences
|
|
cswiki: Masarykův ústav a Archiv Akademie věd České republiky
|
|
wikidata_classification:
|
|
instance_of: &id005
|
|
- id: Q166118
|
|
label: archive
|
|
description: agency or institution responsible for the preservation and communication of records selected for permanent preservation
|
|
- id: Q1664720
|
|
label: institute
|
|
description: organizational body created for a certain purpose
|
|
- id: Q2085381
|
|
label: publishing company
|
|
description: company that prints and distributes pressed goods or electronic media
|
|
- id: Q108935461
|
|
label: Czech research institution
|
|
description: type of Czech research organization
|
|
wikidata_instance_of: *id005
|
|
wikidata_location:
|
|
country: &id006
|
|
id: Q213
|
|
label: Czech Republic
|
|
description: country in Central Europe
|
|
coordinates: &id008
|
|
latitude: 50.1183906
|
|
longitude: 14.4631433
|
|
precision: 1.0e-07
|
|
located_in_admin_entity: &id007
|
|
id: Q1085
|
|
label: Prague
|
|
description: capital city of the Czech Republic
|
|
wikidata_country: *id006
|
|
wikidata_located_in: *id007
|
|
wikidata_coordinates: *id008
|
|
wikidata_organization:
|
|
part_of: &id009
|
|
id: Q374686
|
|
label: Czech Academy of Sciences
|
|
description: academy of sciences
|
|
parent_organization: *id009
|
|
wikidata_web:
|
|
official_website: http://www.mua.cas.cz/
|
|
wikidata_official_website: http://www.mua.cas.cz/
|
|
wikidata_social_media:
|
|
facebook_id: masaryk.avcr
|
|
wikidata_media:
|
|
image: Praha 8, Gabčíkova - MUA, Archiv Akademie věd České republiky.jpg
|
|
logo: Praha, Gabčíkova, objekt Akademie věd České republiky, nápis (2).jpg
|
|
commons_category: Masaryk Institute and Archives of the Czech Academy of Sciences
|
|
wikidata_image: Praha 8, Gabčíkova - MUA, Archiv Akademie věd České republiky.jpg
|
|
wikidata_logo: Praha, Gabčíkova, objekt Akademie věd České republiky, nápis (2).jpg
|
|
wikidata_collection:
|
|
collection_items_count: '3755'
|
|
_provenance:
|
|
content_hash:
|
|
algorithm: sha256
|
|
value: sha256-pwa7gVAwrSuq+W6+LvRtp5x3xsm96AYqer68qrBBvG8=
|
|
scope: enrichment_section
|
|
computed_at: '2025-12-28T19:58:20.926216+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/Q26832919
|
|
verification:
|
|
status: verified
|
|
last_verified: '2025-12-28T19:58:20.926224+00:00'
|
|
location:
|
|
latitude: 50.1183906
|
|
longitude: 14.4631433
|
|
coordinate_provenance:
|
|
source_type: WIKIDATA
|
|
source_path: wikidata_enrichment.wikidata_coordinates
|
|
original_timestamp: '2025-12-08T23:41:49.831054+00:00'
|
|
api_endpoint: https://www.wikidata.org/w/rest.php/wikibase/v1
|
|
entity_id: Q26832919
|
|
region: CZ-10
|
|
region_code: '10'
|
|
country: CZ
|
|
geonames_id: 3068455
|
|
normalization_timestamp: '2025-12-09T06:49:31.790266+00:00'
|
|
youtube_status: NOT_FOUND
|
|
youtube_search_query: Masarykův ústav a Archiv Akademie věd České republiky v.v.i. official
|
|
youtube_search_timestamp: '2025-12-09T09:29:39.442991+00:00'
|
|
logo_enrichment:
|
|
enrichment_timestamp: '2025-12-23T20:19:08.054373+00:00'
|
|
source_url: http://www.mua.cas.cz
|
|
extraction_method: crawl4ai
|
|
claims:
|
|
- claim_type: favicon_url
|
|
claim_value: http://www.mua.cas.cz/build/favicon/safari-pinned-tab.svg
|
|
source_url: http://www.mua.cas.cz
|
|
css_selector: '[document] > html > head > link:nth-of-type(7)'
|
|
retrieved_on: '2025-12-23T20:19:08.054373+00:00'
|
|
extraction_method: crawl4ai_link_rel
|
|
favicon_type: ''
|
|
favicon_sizes: ''
|
|
- claim_type: og_image_url
|
|
claim_value: https://mua.greendot.cz/build/img/hp-hero.jpg
|
|
source_url: http://www.mua.cas.cz
|
|
css_selector: '[document] > html > head > meta:nth-of-type(10)'
|
|
retrieved_on: '2025-12-23T20:19:08.054373+00:00'
|
|
extraction_method: crawl4ai_meta_og
|
|
summary:
|
|
total_claims: 2
|
|
has_primary_logo: false
|
|
has_favicon: true
|
|
has_og_image: true
|
|
favicon_count: 4
|