180 lines
6.1 KiB
YAML
180 lines
6.1 KiB
YAML
original_entry:
|
|
name: The Institute of Cetacean Research
|
|
institution_type: LIBRARY
|
|
source: CH-Annotator (japan_complete_ch_annotator.yaml)
|
|
identifiers:
|
|
- &id001
|
|
identifier_scheme: ISIL
|
|
identifier_value: JP-1005554
|
|
- &id002
|
|
identifier_scheme: Website
|
|
identifier_value: http://www.icrwhale.org
|
|
identifier_url: http://www.icrwhale.org
|
|
locations:
|
|
- country: JP
|
|
city: Chuo Ku
|
|
region: Tokyo To
|
|
postal_code: 104-0055
|
|
street_address: 4-5 TOYOMICHO, Chuo Ku, Tokyo To, 104-0055
|
|
processing_timestamp: '2025-12-06T23:38:58.920219+00:00'
|
|
ghcid:
|
|
ghcid_current: JP-13-CHU-L-ICR
|
|
ghcid_original: JP-TO-CHU-L-ICR
|
|
ghcid_uuid: e5ef7a96-4c79-5ab4-8883-91928011131e
|
|
ghcid_uuid_sha256: 70c044a8-8e2b-81e5-afa4-858ccbdb63f5
|
|
ghcid_numeric: 8124569218506764773
|
|
record_id: 425a1646-dbb9-40f1-89a2-b00e0aab7e5c
|
|
generation_timestamp: '2025-12-06T23:38:58.920219+00:00'
|
|
location_resolution:
|
|
country_code: JP
|
|
region_code: 13
|
|
city_code: CHU
|
|
method: CH_ANNOTATOR_SOURCE
|
|
ghcid_history:
|
|
- ghcid: JP-13-CHU-L-ICR
|
|
valid_from: '2025-12-10T09:44:01Z'
|
|
valid_to: null
|
|
reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO
|
|
3166-2:JP
|
|
- ghcid: JP-TO-CHU-L-ICR
|
|
valid_from: null
|
|
valid_to: '2025-12-10T09:44:01Z'
|
|
reason: Previous GHCID with incorrect region code
|
|
- ghcid: JP-TO-CHU-L-ICR
|
|
ghcid_numeric: 8124569218506764773
|
|
valid_from: '2025-12-06T23:38:58.920219+00:00'
|
|
reason: Initial GHCID from CH-Annotator (japan_complete_ch_annotator.yaml)
|
|
custodian_name:
|
|
claim_type: custodian_name
|
|
claim_value: The Institute of Cetacean Research
|
|
source_type: ch_annotator
|
|
identifiers:
|
|
- identifier_scheme: GHCID
|
|
identifier_value: JP-13-CHU-L-ICR
|
|
- identifier_scheme: GHCID_UUID
|
|
identifier_value: e5ef7a96-4c79-5ab4-8883-91928011131e
|
|
- identifier_scheme: GHCID_UUID_SHA256
|
|
identifier_value: 70c044a8-8e2b-81e5-afa4-858ccbdb63f5
|
|
- identifier_scheme: GHCID_NUMERIC
|
|
identifier_value: '8124569218506764773'
|
|
- identifier_scheme: RECORD_ID
|
|
identifier_value: 425a1646-dbb9-40f1-89a2-b00e0aab7e5c
|
|
- *id001
|
|
- *id002
|
|
provenance:
|
|
data_source: CSV_REGISTRY
|
|
data_tier: TIER_1_AUTHORITATIVE
|
|
extraction_date: '2025-11-18T14:46:40.605376+00:00'
|
|
extraction_method: 'Created from CH-Annotator file: japan_complete_ch_annotator.yaml'
|
|
confidence_score: 0.98
|
|
notes:
|
|
- Canonical location added via normalize_custodian_files.py on 2025-12-08T23:14:52Z
|
|
- Canonical location added via normalize_custodian_files.py on 2025-12-09T06:57:32Z
|
|
ch_annotator:
|
|
convention_id: ch_annotator-v1_7_0
|
|
convention_version: 1.7.0
|
|
entity_classification:
|
|
hypernym: GRP
|
|
hypernym_label: GROUP
|
|
subtype: GRP.HER.LIB
|
|
subtype_label: LIBRARY
|
|
ontology_class: schema:Library
|
|
alternative_classes:
|
|
- org:FormalOrganization
|
|
- rov:RegisteredOrganization
|
|
- glam:HeritageCustodian
|
|
extraction_provenance:
|
|
namespace: glam
|
|
path: /files/japan_complete.yaml
|
|
timestamp: '2025-11-18T14:46:40.605376+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
annotation_provenance:
|
|
annotation_agent: opencode-claude-sonnet-4
|
|
annotation_date: '2025-12-06T21:13:31.304940+00:00'
|
|
annotation_method: retroactive CH-Annotator application via batch script
|
|
source_file: japan_complete.yaml
|
|
annotation_metadata:
|
|
confidence_score: 0.98
|
|
verified: false
|
|
verification_date: null
|
|
verified_by: null
|
|
entity_claims:
|
|
- claim_type: full_name
|
|
claim_value: The Institute of Cetacean Research
|
|
property_uri: skos:prefLabel
|
|
provenance:
|
|
namespace: glam
|
|
path: /files/japan_complete.yaml
|
|
timestamp: '2025-11-18T14:46:40.605376+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 0.98
|
|
- claim_type: institution_type
|
|
claim_value: LIBRARY
|
|
property_uri: rdf:type
|
|
provenance:
|
|
namespace: glam
|
|
path: /files/japan_complete.yaml
|
|
timestamp: '2025-11-18T14:46:40.605376+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 0.95
|
|
- claim_type: located_in_city
|
|
claim_value: Chuo Ku
|
|
property_uri: schema:addressLocality
|
|
provenance:
|
|
namespace: glam
|
|
path: /files/japan_complete.yaml
|
|
timestamp: '2025-11-18T14:46:40.605376+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 0.9
|
|
integration_note:
|
|
created_from: japan_complete_ch_annotator.yaml
|
|
creation_date: '2025-12-06T23:38:58.920219+00:00'
|
|
creation_method: create_custodian_from_ch_annotator.py
|
|
location:
|
|
city: Chuo Ku
|
|
region: Tokyo To
|
|
region_code: 13
|
|
country: JP
|
|
postal_code: 104-0055
|
|
street_address: 4-5 TOYOMICHO, Chuo Ku, Tokyo To, 104-0055
|
|
normalization_timestamp: '2025-12-09T15:23:41.889278+00:00'
|
|
latitude: 35.67004
|
|
longitude: 139.77544
|
|
coordinate_provenance:
|
|
source_type: GEONAMES_LOCAL
|
|
source_path: data/reference/geonames.db
|
|
entity_id: 13353695
|
|
original_timestamp: '2025-12-09T15:23:41.889240+00:00'
|
|
geonames_id: 13353695
|
|
geonames_name: Chūō
|
|
feature_code: PPLA2
|
|
logo_enrichment:
|
|
enrichment_timestamp: '2025-12-24T23:55:01.983351+00:00'
|
|
source_url: http://www.icrwhale.org
|
|
extraction_method: crawl4ai
|
|
claims:
|
|
- claim_type: logo_url
|
|
claim_value: http://www.icrwhale.org/img/logo.png
|
|
source_url: http://www.icrwhale.org
|
|
css_selector: '[document] > html > body > header > div.top_header.lang_box > div.logo_left
|
|
> div.logo_text_flex > div > img.logo_box'
|
|
retrieved_on: '2025-12-24T23:55:01.983351+00:00'
|
|
extraction_method: crawl4ai_header_logo
|
|
detection_confidence: high
|
|
alt_text: 一般財団法人 日本鯨類研究所 ロゴマーク
|
|
- claim_type: og_image_url
|
|
claim_value: https://icrwhale.org/img/ogp.jpg
|
|
source_url: http://www.icrwhale.org
|
|
css_selector: '[document] > html > head > meta:nth-of-type(8)'
|
|
retrieved_on: '2025-12-24T23:55:01.983351+00:00'
|
|
extraction_method: crawl4ai_meta_og
|
|
summary:
|
|
total_claims: 2
|
|
has_primary_logo: true
|
|
has_favicon: false
|
|
has_og_image: true
|
|
favicon_count: 0
|