307 lines
14 KiB
YAML
307 lines
14 KiB
YAML
original_entry:
|
||
name: Archiv Ministerstva vnitra ČR
|
||
institution_type: ARCHIVE
|
||
source: CH-Annotator (czech_unified_ch_annotator.yaml)
|
||
identifiers:
|
||
- &id001
|
||
identifier_scheme: ARON_UUID
|
||
identifier_value: 59e4ab94-3685-4dc5-ba3f-af83e72769f0
|
||
identifier_url: https://portal.nacr.cz/aron/apu/59e4ab94-3685-4dc5-ba3f-af83e72769f0
|
||
- &id002
|
||
identifier_scheme: INSTITUTION_CODE
|
||
identifier_value: '700000070'
|
||
locations: []
|
||
processing_timestamp: '2025-12-06T23:37:44.159335+00:00'
|
||
ghcid:
|
||
ghcid_current: CZ-10-PRA-A-AMVC
|
||
ghcid_original: XX-XX-XXX-A-AMVČ
|
||
ghcid_uuid: 3e7a8dc1-388e-5678-93fc-879fb0add0dc
|
||
ghcid_uuid_sha256: 748b9d99-faed-8055-90e7-cfee838d0153
|
||
ghcid_numeric: 8397979214827831381
|
||
record_id: ce71df01-9e7e-4313-a591-1e84c5bfacd3
|
||
generation_timestamp: '2025-12-06T23:37:44.159335+00:00'
|
||
location_resolution:
|
||
country_code: CZ
|
||
region_code: 10
|
||
city_code: PRA
|
||
method: NAME_PATTERN_EXTRACTION
|
||
resolution_timestamp: '2025-12-06T23:56:11.844094+00:00'
|
||
ghcid_history:
|
||
- ghcid: CZ-10-PRA-A-AMVC
|
||
ghcid_numeric: 8397979214827831381
|
||
valid_from: '2025-12-08T11:21:35.973712+00:00'
|
||
reason: 'Normalized diacritics to ASCII per ABBREV-DIACRITICS rule (was: CZ-10-PRA-A-AMVČ)'
|
||
- ghcid: XX-XX-XXX-A-AMVČ
|
||
ghcid_numeric: 12391615612894528793
|
||
valid_from: '2025-12-06T23:37:44.159335+00:00'
|
||
reason: Initial GHCID from CH-Annotator (czech_unified_ch_annotator.yaml)
|
||
valid_to: '2025-12-08T11:21:35.973712+00:00'
|
||
- ghcid: CZ-XX-XXX-A-AMVČ
|
||
valid_from: '2025-12-06T23:56:11.844111+00:00'
|
||
reason: 'Country resolved via Wikidata P17: XX→CZ'
|
||
- ghcid: CZ-10-PRA-A-AMVČ
|
||
valid_from: '2025-12-07T12:39:42.482491+00:00'
|
||
reason: 'Location resolved from institution name pattern: ''Prague'' → region 10, city PRA'
|
||
custodian_name:
|
||
claim_type: custodian_name
|
||
claim_value: Archiv Ministerstva vnitra ČR
|
||
source_type: ch_annotator
|
||
identifiers:
|
||
- identifier_scheme: GHCID
|
||
identifier_value: CZ-10-PRA-A-AMVC
|
||
- identifier_scheme: GHCID_UUID
|
||
identifier_value: 3e7a8dc1-388e-5678-93fc-879fb0add0dc
|
||
- identifier_scheme: GHCID_UUID_SHA256
|
||
identifier_value: 748b9d99-faed-8055-90e7-cfee838d0153
|
||
- identifier_scheme: GHCID_NUMERIC
|
||
identifier_value: '8397979214827831381'
|
||
- identifier_scheme: RECORD_ID
|
||
identifier_value: ce71df01-9e7e-4313-a591-1e84c5bfacd3
|
||
- *id001
|
||
- *id002
|
||
provenance:
|
||
data_source: API_SCRAPING
|
||
data_tier: TIER_1_AUTHORITATIVE
|
||
extraction_date: '2025-11-19T11:35:45.744134+00:00'
|
||
extraction_method: 'Created from CH-Annotator file: czech_unified_ch_annotator.yaml'
|
||
confidence_score: 0.85
|
||
notes:
|
||
- 'Country resolved 2025-12-06T23:56:11Z: XX→CZ via Wikidata P17'
|
||
- 'YouTube/Google Maps enrichment 2025-12-08T19:45:59Z: Maps: National Archive (conf: 0.80); YouTube: not found'
|
||
- Canonical location added via normalize_custodian_files.py on 2025-12-08T23:11:19Z
|
||
- Canonical location added via normalize_custodian_files.py on 2025-12-08T23:48:04Z
|
||
- Canonical location added via normalize_custodian_files.py on 2025-12-09T06:49:27Z
|
||
schema_version: 2.0.0
|
||
enrichment_provenance:
|
||
google_maps_enrichment:
|
||
content_hash: sha256-pJ8kGGB9vVvUC4S0w8tTKy9bilhgBC8Xi0HvDBpuaLQ=
|
||
verified_at: '2025-12-28T19:58:21.038994+00:00'
|
||
provenance_schema_version: '2.0'
|
||
standards_compliance:
|
||
- W3C PROV-O
|
||
- W3C SRI (content hashes)
|
||
generated_at: '2025-12-28T19:58:21.039012+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
|
||
agent: batch-script-create-custodian-from-ch-annotator
|
||
context_convention: ch_annotator-v1_7_0
|
||
source_archived_at: '2025-11-19T11:35:45.744134+00:00'
|
||
statement_created_at: '2025-12-06T21:12:32.389491+00:00'
|
||
source_type: library_registry_api
|
||
migration_note: Migrated from agent:claude-conversation on 2025-12-30
|
||
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: null
|
||
verified_by: null
|
||
entity_claims:
|
||
- claim_type: full_name
|
||
claim_value: Archiv Ministerstva vnitra ČR
|
||
property_uri: skos:prefLabel
|
||
provenance:
|
||
namespace: glam
|
||
path: /files/czech_unified.yaml
|
||
agent: batch-script-create-custodian-from-ch-annotator
|
||
context_convention: ch_annotator-v1_7_0
|
||
source_archived_at: '2025-11-19T11:35:45.744134+00:00'
|
||
statement_created_at: '2025-12-06T21:12:32.389491+00:00'
|
||
source_type: library_registry_api
|
||
migration_note: Migrated from agent:claude-conversation on 2025-12-30
|
||
confidence: 0.85
|
||
- claim_type: institution_type
|
||
claim_value: ARCHIVE
|
||
property_uri: rdf:type
|
||
provenance:
|
||
namespace: glam
|
||
path: /files/czech_unified.yaml
|
||
agent: batch-script-create-custodian-from-ch-annotator
|
||
context_convention: ch_annotator-v1_7_0
|
||
source_archived_at: '2025-11-19T11:35:45.744134+00:00'
|
||
statement_created_at: '2025-12-06T21:12:32.389491+00:00'
|
||
source_type: library_registry_api
|
||
migration_note: Migrated from agent:claude-conversation on 2025-12-30
|
||
confidence: 0.95
|
||
integration_note:
|
||
created_from: czech_unified_ch_annotator.yaml
|
||
creation_date: '2025-12-06T23:37:44.159335+00:00'
|
||
creation_method: create_custodian_from_ch_annotator.py
|
||
google_maps_enrichment:
|
||
place_id: ChIJza5ArCGVC0cRc9x2Qe6Tuos
|
||
name: National Archive
|
||
fetch_timestamp: '2025-12-08T19:45:55.984101+00:00'
|
||
api_status: OK
|
||
coordinates:
|
||
latitude: 50.096012099999996
|
||
longitude: 14.4015668
|
||
formatted_address: 133, M. Horákové 5, 160 00 Praha 6-Hradčany, Czechia
|
||
short_address: M. Horákové 5, Praha 6-Hradčany
|
||
phone_local: 974 847 839
|
||
phone_international: +420 974 847 839
|
||
website: http://www.nacr.cz/
|
||
google_place_types:
|
||
- library
|
||
- point_of_interest
|
||
- establishment
|
||
business_status: OPERATIONAL
|
||
rating: 4.8
|
||
total_ratings: 12
|
||
reviews:
|
||
- author_name: Anton van Uttenhoven
|
||
author_uri: https://www.google.com/maps/contrib/107425710254765644916/reviews
|
||
rating: 5
|
||
relative_time_description: 10 months ago
|
||
text: The staff are always very friendly. There's even a lady who speaks English very well. Even without the language,
|
||
you can communicate. Everyone is helpful and extremely customer-friendly. I enjoy coming here.
|
||
publish_time: '2025-02-06T21:43:14.918876Z'
|
||
- author_name: Barunka G.
|
||
author_uri: https://www.google.com/maps/contrib/102003756317069132015/reviews
|
||
rating: 4
|
||
relative_time_description: 5 years ago
|
||
text: In the research room of the 1st department (Milady Horákové Street), they are very helpful and willing to help you
|
||
search for archival materials.
|
||
publish_time: '2020-08-12T16:42:30.619293Z'
|
||
- author_name: Kamila Svobodova
|
||
author_uri: https://www.google.com/maps/contrib/109299302074939194601/reviews
|
||
rating: 5
|
||
relative_time_description: 8 years ago
|
||
text: All the archive staff I met were very helpful.
|
||
publish_time: '2017-07-09T09:44:18.601Z'
|
||
- author_name: Оксана Салова
|
||
author_uri: https://www.google.com/maps/contrib/115491272362274042105/reviews
|
||
rating: 5
|
||
relative_time_description: 6 months ago
|
||
text: null
|
||
publish_time: '2025-05-19T14:53:29.081449Z'
|
||
- author_name: Martin Kovalský
|
||
author_uri: https://www.google.com/maps/contrib/112960052014435858055/reviews
|
||
rating: 5
|
||
relative_time_description: 8 years ago
|
||
text: you will find everything there
|
||
publish_time: '2017-03-07T13:02:29.774Z'
|
||
opening_hours:
|
||
open_now: false
|
||
weekday_text:
|
||
- 'Monday: 9:00 AM – 6:00 PM'
|
||
- 'Tuesday: 9:00 AM – 4:00 PM'
|
||
- 'Wednesday: 9:00 AM – 6:00 PM'
|
||
- 'Thursday: 9:00 AM – 4:00 PM'
|
||
- 'Friday: Closed'
|
||
- 'Saturday: Closed'
|
||
- 'Sunday: Closed'
|
||
photo_count: 10
|
||
photos_metadata:
|
||
- name: places/ChIJza5ArCGVC0cRc9x2Qe6Tuos/photos/AZLasHqBe_j2d3nuUAllq2OwYphrNQH1BE3qcHjBNCdCKVQyrJ1Cn8Kkiuy1KVZWPjqf4UI6dpRkGtanq3hwSYLFOf-D6V0r7yVNbtntvrz0qClLV-tJC9XiW0hHUsbvhTNCNBMcicCXOJE9JQc--Pkq-5O5oOBylvSUipkJejwD6npQT3eMNkNLWcyIi2eOWivjTuwgA3QJF4c7f0yiO69p-Wc8PtGf1zrBefSvVM2enqHFSwRzb6ktwNLwyZqTGi74nVR4ilIl4PXLQSNevMVkSbNzrhfsmY8yHByrfW_DlJxxELz5aDYk2S1Z20BVYWJRNBwhG6eEAVPN-TCQiRh7erRnwE3mQssXiZInKTMwRx6clhdONzx2Jn7tKV68_VsoNw_KJFvU-C_vD1tYeqXBMLcwZgN4-EkEwmuP25tUfw5iuQ
|
||
height: 2268
|
||
width: 4032
|
||
- name: places/ChIJza5ArCGVC0cRc9x2Qe6Tuos/photos/AZLasHrYyl2sur4gBaZBGDSqLK1EdRvbg3jFS2cJGzyOgj7zLISO4rEaHOnNfJJnIuzn8Zl2aFVpe0E5C9bm6ZthBCK2AutWFeAk0VHy-ysAenk_VUw_DOBjFJ3V9ak_unt5D9E2QyrbPlhWw62P6b9OSQ2zhOtDtdBIsoiMWPXKwoBKCtyWOM79A5m-1V1XanxA8uwcH0ZMvkxZUEEAVs9dq88EQlJUknCQQ6HlRWIyThHm5pKm_ZW6vPlqaEemdmuFZP1lDFcOOk2sm3xVYkIjJsjwcLjSakO_7moffPyYcFn8INxOdseOWxjm0i1yyUF1ttbUxc2mJtZc09T1Dcb_PeXHRCjb-QuaGmeg95dsVSbdHs767PKN6rev5Y3BrGLvcxiYLgjnfOvZnSaSiSUYHshwACtDb0FSfnTMkqcIx-_Gogg
|
||
height: 4096
|
||
width: 3072
|
||
- name: places/ChIJza5ArCGVC0cRc9x2Qe6Tuos/photos/AZLasHoJ7dDmw9iVYAcANg05P76F0J83ksT3oF0agAQQxySR7ETs6Drub5yvzTCtnNYk3oePtkcVbXgycfN03Fo6nwIOSqfmnUjR49Aee-VLJUyJ69gdSJpiJ-VVin823GkERJHtbZT2-iMzW634wxyfXrKdhlSA081jXira-37hXcvXgNzKXhF1mxMun23NxHDsiH_HeebMxwOrZGZt-ZyoQE-94J0XQIVL4V2lGKjJqemaF1mXImPri5BYkWwCCN-uFPhcocZmakhawB1Lpp1uu7NUOGv3ZzKF7C6Y2bgm3ixyoYm_Rgdv9O4jTfkG2DkFnZKl0Zq-8uZT2gF97g39gix9Qfo79IQ8mZ6R3XtxDP_2boFx-6Ckf49FFxXQ_joFJFKb5zrY9rxgFgcAyx6D7zzVUMmBMkoDye6Wwb0f1Kws0hA
|
||
height: 3193
|
||
width: 4800
|
||
- name: places/ChIJza5ArCGVC0cRc9x2Qe6Tuos/photos/AZLasHr3Dpbc6gLBeHea-TIV_dCEyPtUGZyapqabJVwV0g3W-J2zvrbvEkJgEHjWZZ7ZEA7_IiuQ7V2---3c3nxcFgQQIumuj6ridThjJ8rEAyr7QfUZjRldBGPT6KvDRIKKCKfahx6Id5VA0a96suGFallimLlekcZxyOT3hAqKnSMH1GPVx0CZeeDWJrDJfew_bjvcgaW5MRmJwNVNNbj_6u2lDefHHCoJ7gZqpn8GVD4fA2vvx_naofXk7tQIViWk_Vz0EtoErevNjENUd8mRN3Bh2967mJ-x6Now1KkDtGgwKutI_cyViKbm3W_EL-m91hCVBYvXy2Y4D-wBDMyIsf05re-IDUP_fq2N17FGR79qoTN5qxERrpD_QBHSYAIFKzCdSF-1vwKvKdlb_KxpySuJMhj-z7cEYjJlLNlzYJg6wnUX
|
||
height: 4080
|
||
width: 3072
|
||
- name: places/ChIJza5ArCGVC0cRc9x2Qe6Tuos/photos/AZLasHrieCgc28jFGc8pvaVks1qXUpOwvOPE1GSrs-9grjapNju51gJZ_TOaqvFrJhvpDByPYvmKez6Clakus5ohMlIEH3gNx8Y34BvBeLBRuo8l3tCiuAyCUmJ0fv3qJS8PGcpvxoxA4zyLWpPvuD1gYTj-LaWlSjJ-NcA2P_AZ1pXkMmZ1-5hZCwTRlO3YvyAJ7NuWier1UZYLVJziV7q0dP41OPGuPKXb0V-GGwYvStUlF4J7HaYbel0_JBv4tZeLeJRM7pEOh8coLR1n8BNM7I9OUFhfO5ehhcxULUE9X0qUf0E3XzhGRjBDdqclETFFeLtsPUoFksNDY6AlBzBkIaxToOelJ1MsVlrLZtBKx05i60gO3Xtl3dPa03Kt1_MipMK6cFmtd-eXpzCRK83Nlhwi4IHk8RuXgDmUyagoBdrlLQ
|
||
height: 4096
|
||
width: 3072
|
||
google_maps_url: https://maps.google.com/?cid=10068522568449973363&g_mp=Cidnb29nbGUubWFwcy5wbGFjZXMudjEuUGxhY2VzLlNlYXJjaFRleHQQAhgEIAA
|
||
llm_verification:
|
||
is_match: true
|
||
confidence: 0.8
|
||
entity_type: GRP.HER
|
||
reasoning: 'NAME MATCH: The candidate name ''National Archive'' is a general but plausible English translation for the
|
||
source ''Archiv Ministerstva vnitra ČR''. The website nacr.cz confirms it is the National Archives of the Czech Republic,
|
||
which aligns with the source being a ministry archive. LOCATION MATCH: The address is in Praha (Prague), Czechia, matching
|
||
the expected country ''CZ''. TYPE MATCH: The Google Place type ''library'' is an acceptable heritage type. The website
|
||
confirms it is an archive institution. ENTITY TYPE: It is a heritage institution (archive). Confidence is not 1.0 due
|
||
to the generic English name and lack of a more direct name translation, but the evidence strongly supports a match.'
|
||
agent: glm-4.6
|
||
verified: true
|
||
ch_annotator_version: ch_annotator-v1_7_0
|
||
_provenance:
|
||
content_hash:
|
||
algorithm: sha256
|
||
value: sha256-pJ8kGGB9vVvUC4S0w8tTKy9bilhgBC8Xi0HvDBpuaLQ=
|
||
scope: enrichment_section
|
||
computed_at: '2025-12-28T19:58:21.038994+00:00'
|
||
prov:
|
||
wasDerivedFrom: https://maps.googleapis.com/maps/api/place/details/json?place_id=ChIJza5ArCGVC0cRc9x2Qe6Tuos
|
||
generatedAtTime: '2025-12-08T19:45:55.984101+00:00'
|
||
wasGeneratedBy:
|
||
'@type': prov:Activity
|
||
name: google_maps_api_fetch
|
||
used: https://maps.googleapis.com/maps/api/place
|
||
verification:
|
||
status: verified
|
||
last_verified: '2025-12-28T19:58:21.039002+00:00'
|
||
google_maps_status: SUCCESS
|
||
youtube_status: NOT_FOUND
|
||
youtube_search_query: Archiv Ministerstva vnitra ČR official
|
||
youtube_search_timestamp: '2025-12-08T19:45:59.493700+00:00'
|
||
location:
|
||
latitude: 50.096012099999996
|
||
longitude: 14.4015668
|
||
coordinate_provenance:
|
||
source_type: GOOGLE_MAPS
|
||
source_path: google_maps_enrichment.coordinates
|
||
original_timestamp: '2025-12-08T19:45:55.984101+00:00'
|
||
entity_id: ChIJza5ArCGVC0cRc9x2Qe6Tuos
|
||
region_code: 10
|
||
country: CZ
|
||
street_address: M. Horákové 5, Praha 6-Hradčany
|
||
formatted_address: 133, M. Horákové 5, 160 00 Praha 6-Hradčany, Czechia
|
||
normalization_timestamp: '2025-12-09T06:49:27.868521+00:00'
|
||
logo_enrichment:
|
||
enrichment_timestamp: '2025-12-23T20:19:31.631386+00:00'
|
||
source_url: http://www.nacr.cz
|
||
extraction_method: crawl4ai
|
||
claims:
|
||
- claim_type: logo_url
|
||
claim_value: https://www.nacr.cz/wp-content/themes/narodni_archiv/img/logo_na_en.png
|
||
source_url: http://www.nacr.cz
|
||
css_selector: '#wrapper-navbar > header.header > div.header__main:nth-of-type(2) > nav.navbar.navbar-expand-lg > div.navbar-mobile-top
|
||
> div.navbar-brand > a > img'
|
||
retrieved_on: '2025-12-23T20:19:31.631386+00:00'
|
||
extraction_method: crawl4ai_header_logo
|
||
detection_confidence: high
|
||
alt_text: National Archives
|
||
- claim_type: favicon_url
|
||
claim_value: https://www.nacr.cz/wp-content/themes/narodni_archiv/img/favicon/apple-icon-180x180.png
|
||
source_url: http://www.nacr.cz
|
||
css_selector: '[document] > html > head > link:nth-of-type(9)'
|
||
retrieved_on: '2025-12-23T20:19:31.631386+00:00'
|
||
extraction_method: crawl4ai_link_rel
|
||
favicon_type: ''
|
||
favicon_sizes: 180x180
|
||
- claim_type: og_image_url
|
||
claim_value: https://www.nacr.cz/wp-content/uploads/2020/04/podatelna2_22-1.jpg
|
||
source_url: http://www.nacr.cz
|
||
css_selector: '[document] > html > head > meta:nth-of-type(17)'
|
||
retrieved_on: '2025-12-23T20:19:31.631386+00:00'
|
||
extraction_method: crawl4ai_meta_og
|
||
summary:
|
||
total_claims: 3
|
||
has_primary_logo: true
|
||
has_favicon: true
|
||
has_og_image: true
|
||
favicon_count: 13
|