enrich japanese and dutch custodians

This commit is contained in:
kempersc 2025-12-23 18:08:45 +01:00
parent a1fb6344e7
commit 5e8a432ef0
111 changed files with 2378 additions and 110 deletions

View file

@ -448,6 +448,41 @@ class DSPyQueryRequest(BaseModel):
)
class LLMResponseMetadata(BaseModel):
"""LLM response provenance metadata (aligned with LinkML LLMResponse schema).
Captures GLM 4.7 Interleaved Thinking chain-of-thought reasoning and
full API response metadata for audit trails and debugging.
See: schemas/20251121/linkml/modules/classes/LLMResponse.yaml
"""
# Core response content
content: str | None = None # The final LLM response text
reasoning_content: str | None = None # GLM 4.7 Interleaved Thinking chain-of-thought
# Model identification
model: str | None = None # Model identifier (e.g., 'glm-4.7', 'claude-3-opus')
provider: str | None = None # Provider enum: zai, anthropic, openai, huggingface, groq
# Request tracking
request_id: str | None = None # Provider-assigned request ID
created: str | None = None # ISO 8601 timestamp of response generation
# Token usage (for cost estimation and monitoring)
prompt_tokens: int | None = None # Tokens in input prompt
completion_tokens: int | None = None # Tokens in response (content + reasoning)
total_tokens: int | None = None # Total tokens used
cached_tokens: int | None = None # Tokens served from provider cache
# Response metadata
finish_reason: str | None = None # stop, length, tool_calls, content_filter
latency_ms: int | None = None # Response latency in milliseconds
# GLM 4.7 Thinking Mode configuration
thinking_mode: str | None = None # enabled, disabled, interleaved, preserved
clear_thinking: bool | None = None # False = Preserved Thinking enabled
class DSPyQueryResponse(BaseModel):
"""DSPy RAG query response."""
question: str
@ -470,6 +505,127 @@ class DSPyQueryResponse(BaseModel):
# Cache tracking
cache_hit: bool = False # Whether response was served from cache
# LLM response provenance (GLM 4.7 Thinking Mode support)
llm_response: LLMResponseMetadata | None = None # Full LLM response metadata including reasoning_content
def extract_llm_response_metadata(
lm: Any,
provider: str | None = None,
latency_ms: int | None = None,
) -> LLMResponseMetadata | None:
"""Extract LLM response metadata from DSPy LM history.
DSPy stores the raw API response in lm.history[-1]["response"], which includes:
- choices[0].message.content (final response text)
- choices[0].message.reasoning_content (GLM 4.7 Interleaved Thinking)
- usage.prompt_tokens, completion_tokens, total_tokens
- model, created, id, finish_reason
This enables capturing GLM 4.7's chain-of-thought reasoning for provenance.
Args:
lm: DSPy LM instance with history attribute
provider: LLM provider name (zai, anthropic, openai, etc.)
latency_ms: Response latency in milliseconds
Returns:
LLMResponseMetadata or None if history is empty
"""
try:
# Check if LM has history
if not hasattr(lm, "history") or not lm.history:
logger.debug("No LM history available for metadata extraction")
return None
# Get the last history entry (most recent LLM call)
last_entry = lm.history[-1]
response = last_entry.get("response")
if response is None:
logger.debug("No response in LM history entry")
return None
# Extract content and reasoning_content from the response
content = None
reasoning_content = None
finish_reason = None
if hasattr(response, "choices") and response.choices:
choice = response.choices[0]
if hasattr(choice, "message"):
message = choice.message
content = getattr(message, "content", None)
# GLM 4.7 Interleaved Thinking - check for reasoning_content
reasoning_content = getattr(message, "reasoning_content", None)
elif isinstance(choice, dict):
content = choice.get("text") or choice.get("message", {}).get("content")
reasoning_content = choice.get("message", {}).get("reasoning_content")
# Extract finish_reason
finish_reason = getattr(choice, "finish_reason", None)
if finish_reason is None and isinstance(choice, dict):
finish_reason = choice.get("finish_reason")
# Extract usage statistics
usage = last_entry.get("usage", {})
prompt_tokens = usage.get("prompt_tokens")
completion_tokens = usage.get("completion_tokens")
total_tokens = usage.get("total_tokens")
# Check for cached_tokens (some providers include this)
cached_tokens = None
if "prompt_tokens_details" in usage:
cached_tokens = usage["prompt_tokens_details"].get("cached_tokens")
# Extract model info
model = last_entry.get("response_model") or last_entry.get("model")
request_id = getattr(response, "id", None)
created = getattr(response, "created", None)
# Convert unix timestamp to ISO 8601 if needed
created_str = None
if created:
if isinstance(created, (int, float)):
import datetime
created_str = datetime.datetime.fromtimestamp(created, tz=datetime.timezone.utc).isoformat()
else:
created_str = str(created)
# Determine thinking mode (GLM 4.7 specific)
thinking_mode = None
if reasoning_content:
# If we got reasoning_content, the model used interleaved thinking
thinking_mode = "interleaved"
metadata = LLMResponseMetadata(
content=content,
reasoning_content=reasoning_content,
model=model,
provider=provider,
request_id=request_id,
created=created_str,
prompt_tokens=prompt_tokens,
completion_tokens=completion_tokens,
total_tokens=total_tokens,
cached_tokens=cached_tokens,
finish_reason=finish_reason,
latency_ms=latency_ms,
thinking_mode=thinking_mode,
)
if reasoning_content:
logger.info(
f"Captured GLM 4.7 reasoning_content ({len(reasoning_content)} chars) "
f"from {provider}/{model}"
)
return metadata
except Exception as e:
logger.warning(f"Failed to extract LLM response metadata: {e}")
return None
# Cache Client
@ -2292,6 +2448,13 @@ async def dspy_query(request: DSPyQueryRequest) -> DSPyQueryResponse:
retrieved_results = getattr(result, "retrieved_results", None)
query_type = getattr(result, "query_type", None)
# Extract LLM response metadata from DSPy history (GLM 4.7 reasoning_content support)
llm_response_metadata = extract_llm_response_metadata(
lm=lm,
provider=llm_provider_used,
latency_ms=int(elapsed_ms),
)
# Build response object
response = DSPyQueryResponse(
question=request.question,
@ -2312,6 +2475,8 @@ async def dspy_query(request: DSPyQueryRequest) -> DSPyQueryResponse:
llm_provider_used=llm_provider_used,
llm_model_used=llm_model_used,
cache_hit=False,
# LLM response provenance (GLM 4.7 Thinking Mode chain-of-thought)
llm_response=llm_response_metadata,
)
# Cache the successful response for future requests
@ -2767,6 +2932,13 @@ async def stream_dspy_query_response(
retrieved_results = getattr(result, "retrieved_results", None)
query_type = getattr(result, "query_type", None)
# Extract LLM response metadata from DSPy history (GLM 4.7 reasoning_content support)
llm_response_metadata = extract_llm_response_metadata(
lm=lm,
provider=llm_provider_used,
latency_ms=int(elapsed_ms),
)
response = DSPyQueryResponse(
question=request.question,
resolved_question=getattr(result, "resolved_question", None),
@ -2784,6 +2956,8 @@ async def stream_dspy_query_response(
llm_provider_used=llm_provider_used,
llm_model_used=llm_model_used,
cache_hit=False,
# LLM response provenance (GLM 4.7 Thinking Mode chain-of-thought)
llm_response=llm_response_metadata,
)
# Cache the response

View file

@ -6506,7 +6506,157 @@
"JP-05-AKI-M-AO.yaml",
"JP-05-AKI-M-APCH.yaml",
"JP-05-AKI-M-MIMAU.yaml",
"JP-05-AKI-M-NSLC.yaml"
"JP-05-AKI-M-NSLC.yaml",
"JP-05-AKI-M-OKFH.yaml",
"JP-05-AKI-M-SCFM.yaml",
"JP-05-AMA-M-KFHM.yaml",
"JP-05-DAI-A-DCA.yaml",
"JP-05-DAI-L-DL-daisenshiritsukamioka_library.yaml",
"JP-05-DAI-L-DL-daisenshiritsukyowa_library.yaml",
"JP-05-DAI-L-DL-daisenshiritsunakasen_library.yaml",
"JP-05-DAI-L-DL-daisenshiritsunangai_library.yaml",
"JP-05-DAI-L-DL-daisenshiritsunishisemboku_library.yaml",
"JP-05-DAI-L-DL-daisenshiritsuota_library.yaml",
"JP-05-DAI-L-DL-daisenshiritsusemboku_library.yaml",
"JP-05-DAI-L-DL.yaml",
"JP-05-DAI-M-AAC.yaml",
"JP-05-DAI-M-APMAS.yaml",
"JP-05-DAI-M-DSKT.yaml",
"JP-05-DAI-M-HHS.yaml",
"JP-05-DAI-M-HTCPM.yaml",
"JP-05-EBI-M-IC.yaml",
"JP-05-GOR-L-OCL.yaml",
"JP-05-HOJ-M-S.yaml",
"JP-05-HOR-M-MV.yaml",
"JP-05-ISH-M-IJM.yaml",
"JP-05-KAT-L-KL.yaml",
"JP-05-KAT-L-KLI.yaml",
"JP-05-KAT-L-KLO.yaml",
"JP-05-KAT-L-KLS.yaml",
"JP-05-KAT-M-KKIS.yaml",
"JP-05-KAZ-L-KL-kazunoshiritsutateyamabunkokeishotowada_library.yaml",
"JP-05-KAZ-L-KL-kosakachoritsukosaka_library.yaml",
"JP-05-KAZ-L-KL.yaml",
"JP-05-KAZ-M-KCHFM.yaml",
"JP-05-KAZ-M-KCMHM.yaml",
"JP-05-KAZ-M-KPMH.yaml",
"JP-05-KAZ-M-OSCC.yaml",
"JP-05-KIT-L-K-kitaakitashiaikawakominkantoshoshitsu.yaml",
"JP-05-KIT-L-K.yaml",
"JP-05-KIT-L-KL-kamikoanisonritsu_library.yaml",
"JP-05-KIT-L-KL-kitaakitashimoriyoshi_library.yaml",
"JP-05-KIT-L-KL.yaml",
"JP-05-KIT-M-ALTM.yaml",
"JP-05-KIT-M-HUMM.yaml",
"JP-05-KIT-M-KK.yaml",
"JP-05-KIT-M-MS.yaml",
"JP-05-KUM-M-KMA.yaml",
"JP-05-MAN-M-SSM.yaml",
"JP-05-MAT-M-ASRO.yaml",
"JP-05-MAT-M-EUM.yaml",
"JP-05-MIN-L-AO.yaml",
"JP-05-MIN-L-G.yaml",
"JP-05-MIN-L-HL.yaml",
"JP-05-MIN-L-I.yaml",
"JP-05-MIN-L-O.yaml",
"JP-05-MIN-M-GMFM.yaml",
"JP-05-MIN-M-IMHMH.yaml",
"JP-05-MIY-M-OMA.yaml",
"JP-05-NIK-L-NLK.yaml",
"JP-05-NIK-L-NLN.yaml",
"JP-05-NIK-L-NPL.yaml",
"JP-05-NIK-M-CHVC.yaml",
"JP-05-NIK-M-CSFSM.yaml",
"JP-05-NIK-M-KM.yaml",
"JP-05-NIK-M-KSTH.yaml",
"JP-05-NIK-M-NLM.yaml",
"JP-05-NIK-M-TM.yaml",
"JP-05-NOS-L-A.yaml",
"JP-05-NOS-L-N.yaml",
"JP-05-NOS-L-NL.yaml",
"JP-05-NOS-M-IMH.yaml",
"JP-05-NOS-M-NCCSM.yaml",
"JP-05-NOS-M-NEP.yaml",
"JP-05-NYU-M-TLM.yaml",
"JP-05-ODA-L-AL.yaml",
"JP-05-ODA-L-OKL.yaml",
"JP-05-ODA-L-OL-odateshiritsuhinai_library.yaml",
"JP-05-ODA-L-OL-odateshiritsutashiro_library.yaml",
"JP-05-ODA-L-OL.yaml",
"JP-05-ODA-M-MAD.yaml",
"JP-05-ODA-M-OMH.yaml",
"JP-05-OGA-L-H.yaml",
"JP-05-OGA-L-OL.yaml",
"JP-05-OGA-L-UL.yaml",
"JP-05-OGA-L-W.yaml",
"JP-05-OGA-M-HHM.yaml",
"JP-05-OGA-M-HNM.yaml",
"JP-05-OGA-M-NM.yaml",
"JP-05-OGA-M-OCGLC.yaml",
"JP-05-OGA-M-OW.yaml",
"JP-05-OGA-M-UMHM.yaml",
"JP-05-SEM-L-M.yaml",
"JP-05-SEM-L-SG.yaml",
"JP-05-SEM-L-SL.yaml",
"JP-05-SEM-M-HMAM.yaml",
"JP-05-SEM-M-KKM.yaml",
"JP-05-SEM-M-LTKTM.yaml",
"JP-05-SEM-M-MCMH.yaml",
"JP-05-SEM-M-MTMHF.yaml",
"JP-05-SEM-M-NMHML.yaml",
"JP-05-SEM-M-OAM.yaml",
"JP-05-SUM-M-NCHHM.yaml",
"JP-05-TAM-M-TMMAI.yaml",
"JP-05-UWA-M-UCHM.yaml",
"JP-05-YAM-L-F.yaml",
"JP-05-YAM-L-H-happochominehamachikubunkakoryusentahoeikantoshosh.yaml",
"JP-05-YAM-L-H.yaml",
"JP-05-YAM-L-M-mitanechokotokakominkantoshoshitsu.yaml",
"JP-05-YAM-L-M-mitanechoyamamotokominkantoshoshitsu.yaml",
"JP-05-YAM-L-M.yaml",
"JP-05-YOK-A-YCMA-yokote_city_modern_archives.yaml",
"JP-05-YOK-A-YCMA.yaml",
"JP-05-YOK-L-Y-yokoteshiritsutaiyutoshoshitsu.yaml",
"JP-05-YOK-L-Y.yaml",
"JP-05-YOK-L-YL-yokoteshiritsuhiraka_library.yaml",
"JP-05-YOK-L-YL-yokoteshiritsujumonji_library.yaml",
"JP-05-YOK-L-YL-yokoteshiritsumasuda_library.yaml",
"JP-05-YOK-L-YL-yokoteshiritsuomori_library.yaml",
"JP-05-YOK-L-YL.yaml",
"JP-05-YOK-L-YLCL.yaml",
"JP-05-YOK-M-HMYC.yaml",
"JP-05-YOK-M-HTS.yaml",
"JP-05-YOK-M-JHMER.yaml",
"JP-05-YOK-M-OLMH.yaml",
"JP-05-YOK-M-TCHFM.yaml",
"JP-05-YOK-M-YILMH.yaml",
"JP-05-YOK-M-YMMM.yaml",
"JP-05-YUR-L-AH.yaml",
"JP-05-YUR-L-D.yaml",
"JP-05-YUR-L-Y-yurihonjoshichokaikominkantoshoshitsu.yaml",
"JP-05-YUR-L-Y-yurihonjoshihigashiyurikominkantoshoshitsu.yaml",
"JP-05-YUR-L-Y-yurihonjoshiyashimakominkantoshoshitsu.yaml",
"JP-05-YUR-L-Y.yaml",
"JP-05-YUR-L-YL-yurihonjoshiiwaki_library.yaml",
"JP-05-YUR-L-YL-yurihonjoshiyuri_library.yaml",
"JP-05-YUR-L-YL.yaml",
"JP-05-YUR-M-CWTM.yaml",
"JP-05-YUR-M-IFMH.yaml",
"JP-05-YUR-M-KCAMYS.yaml",
"JP-05-YUR-M-OHFMH.yaml",
"JP-05-YUR-M-YMLMM.yaml",
"JP-05-YUR-M-YSYLCPI.yaml",
"JP-05-YUZ-L-Y.yaml",
"JP-05-YUZ-L-YE.yaml",
"JP-05-YUZ-L-YL-yuzawashiritsuogachi_library.yaml",
"JP-05-YUZ-L-YL.yaml",
"JP-05-YUZ-M-ISMM.yaml",
"JP-05-YUZ-M-JYYKT.yaml",
"JP-06-ABA-M-FPIAFSM.yaml",
"JP-06-FUK-L-FL.yaml",
"JP-06-FUK-M-FCHM.yaml",
"JP-06-HAR-M-FJ.yaml",
"JP-06-KIT-M-FCSM.yaml"
],
"last_index": 9
}

View file

@ -480,3 +480,30 @@ location:
geonames_id: 6417058
feature_code: PPL
normalization_timestamp: '2025-12-09T06:53:25.911492+00:00'
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:28:17.289828+00:00'
source_url: https://www.city.imabari.ehime.jp/museum/santou
extraction_method: crawl4ai
claims:
- claim_type: logo_url
claim_value: https://www.city.imabari.ehime.jp/museum/santou/img/logo.gif
source_url: https://www.city.imabari.ehime.jp/museum/santou
css_selector: '#museum_logo > a > img'
retrieved_on: '2025-12-23T16:28:17.289828+00:00'
extraction_method: crawl4ai_header_logo
detection_confidence: high
alt_text: 上浦歴史民俗資料館(村上三島記念館)
- claim_type: favicon_url
claim_value: https://www.city.imabari.ehime.jp/museum/favicon.ico
source_url: https://www.city.imabari.ehime.jp/museum/santou
css_selector: '[document] > html > head > link:nth-of-type(4)'
retrieved_on: '2025-12-23T16:28:17.289828+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
summary:
total_claims: 2
has_primary_logo: true
has_favicon: true
has_og_image: false
favicon_count: 1

View file

@ -38,18 +38,19 @@ ghcid:
generation_timestamp: '2025-12-06T23:38:31.102635+00:00'
location_resolution:
country_code: JP
region_code: 05
region_code: 5
city_code: DAI
method: CH_ANNOTATOR_SOURCE
ghcid_history:
- ghcid: JP-05-DAI-M-AAC
valid_from: "2025-12-10T09:43:29Z"
valid_from: '2025-12-10T09:43:29Z'
valid_to: null
reason: "Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO 3166-2:JP"
reason: Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO
3166-2:JP
- ghcid: JP-AK-DAI-M-AAC
valid_from: null
valid_to: "2025-12-10T09:43:29Z"
reason: "Previous GHCID with incorrect region code"
valid_to: '2025-12-10T09:43:29Z'
reason: Previous GHCID with incorrect region code
- ghcid: JP-AK-DAI-M-AAC
ghcid_numeric: 7831768514642479968
valid_from: '2025-12-06T23:38:31.102635+00:00'
@ -217,8 +218,27 @@ location:
source_path: wikidata_enrichment.wikidata_coordinates
city: Daisen Shi
region: Akita Ken
region_code: 05
region_code: 5
country: *id006
postal_code: 014-0802
street_address: HOTTA, Daisen Shi, Akita Ken, 014-0802
normalization_timestamp: '2025-12-09T10:55:21.771540+00:00'
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:29:36.704689+00:00'
source_url: https://common3.pref.akita.lg.jp/maibun
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: https://common3.pref.akita.lg.jp/apple-touch-icon-180x180.png
source_url: https://common3.pref.akita.lg.jp/maibun
css_selector: '[document] > html > head > link:nth-of-type(5)'
retrieved_on: '2025-12-23T16:29:36.704689+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: 180x180
summary:
total_claims: 1
has_primary_logo: false
has_favicon: true
has_og_image: false
favicon_count: 2

View file

@ -441,3 +441,30 @@ location:
geonames_id: 6416231
feature_code: PPL
normalization_timestamp: '2025-12-09T06:53:26.080731+00:00'
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:29:55.234034+00:00'
source_url: https://www.city.imabari.ehime.jp/museum/imabarijo
extraction_method: crawl4ai
claims:
- claim_type: logo_url
claim_value: https://www.city.imabari.ehime.jp/museum/imabarijo/img/logo.gif
source_url: https://www.city.imabari.ehime.jp/museum/imabarijo
css_selector: '#museum_logo > a > img'
retrieved_on: '2025-12-23T16:29:55.234034+00:00'
extraction_method: crawl4ai_header_logo
detection_confidence: high
alt_text: 今治城
- claim_type: favicon_url
claim_value: https://www.city.imabari.ehime.jp/museum/favicon.ico
source_url: https://www.city.imabari.ehime.jp/museum/imabarijo
css_selector: '[document] > html > head > link:nth-of-type(4)'
retrieved_on: '2025-12-23T16:29:55.234034+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
summary:
total_claims: 2
has_primary_logo: true
has_favicon: true
has_og_image: false
favicon_count: 1

View file

@ -351,3 +351,20 @@ location:
geonames_id: 1926141
feature_code: PPL
normalization_timestamp: '2025-12-09T06:53:26.249401+00:00'
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:30:12.263185+00:00'
source_url: https://www.miuraz.co.jp/miurart
extraction_method: crawl4ai
claims:
- claim_type: og_image_url
claim_value: https://www.miuraz.co.jp/miurart/common/images/ogp.jpg
source_url: https://www.miuraz.co.jp/miurart
css_selector: '[document] > html > head > meta:nth-of-type(7)'
retrieved_on: '2025-12-23T16:30:12.263185+00:00'
extraction_method: crawl4ai_meta_og
summary:
total_claims: 1
has_primary_logo: false
has_favicon: false
has_og_image: true
favicon_count: 0

View file

@ -423,3 +423,22 @@ youtube_enrichment:
comments: []
thumbnail_url: https://i.ytimg.com/vi/A8wWHGGK03A/hqdefault_live.jpg
status: SUCCESS
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:30:19.721950+00:00'
source_url: https://itami-kinenkan.jp
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: https://itami-kinenkan.jp/favicon.ico
source_url: https://itami-kinenkan.jp
css_selector: '[document] > html > head > link:nth-of-type(4)'
retrieved_on: '2025-12-23T16:30:19.721950+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
summary:
total_claims: 1
has_primary_logo: false
has_favicon: true
has_og_image: false
favicon_count: 1

View file

@ -199,3 +199,22 @@ wikidata_enrichment:
wikidata_web:
official_website: http://library.city.katagami.akita.jp
wikidata_official_website: http://library.city.katagami.akita.jp
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:30:26.959687+00:00'
source_url: http://library.city.katagami.akita.jp
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: http://library.city.katagami.akita.jp/favicon.ico
source_url: http://library.city.katagami.akita.jp
css_selector: '[document] > html > head > link'
retrieved_on: '2025-12-23T16:30:26.959687+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: image/x-icon
favicon_sizes: ''
summary:
total_claims: 1
has_primary_logo: false
has_favicon: true
has_og_image: false
favicon_count: 1

View file

@ -200,3 +200,22 @@ wikidata_enrichment:
wikidata_web:
official_website: http://library.city.katagami.akita.jp/
wikidata_official_website: http://library.city.katagami.akita.jp/
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:30:33.904124+00:00'
source_url: http://library.city.katagami.akita.jp
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: http://library.city.katagami.akita.jp/favicon.ico
source_url: http://library.city.katagami.akita.jp
css_selector: '[document] > html > head > link'
retrieved_on: '2025-12-23T16:30:33.904124+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: image/x-icon
favicon_sizes: ''
summary:
total_claims: 1
has_primary_logo: false
has_favicon: true
has_og_image: false
favicon_count: 1

View file

@ -199,3 +199,36 @@ wikidata_enrichment:
wikidata_web:
official_website: http://www.city.katagami.lg.jp/index.cfm/7
wikidata_official_website: http://www.city.katagami.lg.jp/index.cfm/7
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:30:43.017693+00:00'
source_url: http://www.city.katagami.lg.jp/index.cfm/7
extraction_method: crawl4ai
claims:
- claim_type: logo_url
claim_value: http://www.city.katagami.lg.jp/theme/base/img_common/header_logo.png
source_url: http://www.city.katagami.lg.jp/index.cfm/7
css_selector: '#header-logo > a > img'
retrieved_on: '2025-12-23T16:30:43.017693+00:00'
extraction_method: crawl4ai_header_logo
detection_confidence: high
alt_text: 潟上市 Katagami City
- claim_type: favicon_url
claim_value: http://www.city.katagami.lg.jp/theme/base/img_common/smartphone.png
source_url: http://www.city.katagami.lg.jp/index.cfm/7
css_selector: '[document] > html > head > link:nth-of-type(3)'
retrieved_on: '2025-12-23T16:30:43.017693+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
- claim_type: og_image_url
claim_value: http://www.city.katagami.lg.jp/theme/base/img_common/ogp_noimage.png
source_url: http://www.city.katagami.lg.jp/index.cfm/7
css_selector: '[document] > html > head > meta:nth-of-type(8)'
retrieved_on: '2025-12-23T16:30:43.017693+00:00'
extraction_method: crawl4ai_meta_og
summary:
total_claims: 3
has_primary_logo: true
has_favicon: true
has_og_image: true
favicon_count: 2

View file

@ -199,3 +199,22 @@ wikidata_enrichment:
wikidata_web:
official_website: http://library.city.katagami.akita.jp/
wikidata_official_website: http://library.city.katagami.akita.jp/
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:30:50.218350+00:00'
source_url: http://library.city.katagami.akita.jp
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: http://library.city.katagami.akita.jp/favicon.ico
source_url: http://library.city.katagami.akita.jp
css_selector: '[document] > html > head > link'
retrieved_on: '2025-12-23T16:30:50.218350+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: image/x-icon
favicon_sizes: ''
summary:
total_claims: 1
has_primary_logo: false
has_favicon: true
has_og_image: false
favicon_count: 1

View file

@ -201,3 +201,36 @@ wikidata_enrichment:
wikidata_web:
official_website: http://www.town.kosaka.akita.jp/tosho/index.html
wikidata_official_website: http://www.town.kosaka.akita.jp/tosho/index.html
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:31:09.599571+00:00'
source_url: http://www.town.kosaka.akita.jp/tosho/index.html
extraction_method: crawl4ai
claims:
- claim_type: logo_url
claim_value: http://www.town.kosaka.akita.jp/theme/base/img_sub/header_logo_pc.png
source_url: http://www.town.kosaka.akita.jp/tosho/index.html
css_selector: '#header > div.header-in > p.header-logo > a > img'
retrieved_on: '2025-12-23T16:31:09.599571+00:00'
extraction_method: crawl4ai_header_logo
detection_confidence: high
alt_text: 秋田県小坂町 Kosaka Town Official Site ひとと自然と文化を未来につなぐ 魅力あふれるまち
- claim_type: favicon_url
claim_value: http://www.town.kosaka.akita.jp/theme/base/img_common/smartphone.png
source_url: http://www.town.kosaka.akita.jp/tosho/index.html
css_selector: '[document] > html > head > link:nth-of-type(3)'
retrieved_on: '2025-12-23T16:31:09.599571+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
- claim_type: og_image_url
claim_value: http://www.town.kosaka.akita.jp/theme/base/img_common/ogp_noimage.png
source_url: http://www.town.kosaka.akita.jp/tosho/index.html
css_selector: '[document] > html > head > meta:nth-of-type(8)'
retrieved_on: '2025-12-23T16:31:09.599571+00:00'
extraction_method: crawl4ai_meta_og
summary:
total_claims: 3
has_primary_logo: true
has_favicon: true
has_og_image: true
favicon_count: 2

View file

@ -32,18 +32,19 @@ ghcid:
generation_timestamp: '2025-12-06T23:38:31.078680+00:00'
location_resolution:
country_code: JP
region_code: 05
region_code: 5
city_code: KAZ
method: CH_ANNOTATOR_SOURCE
ghcid_history:
- ghcid: JP-05-KAZ-M-OSCC
valid_from: "2025-12-10T09:43:29Z"
valid_from: '2025-12-10T09:43:29Z'
valid_to: null
reason: "Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO 3166-2:JP"
reason: Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO
3166-2:JP
- ghcid: JP-AK-KAZ-M-OSCC
valid_from: null
valid_to: "2025-12-10T09:43:29Z"
reason: "Previous GHCID with incorrect region code"
valid_to: '2025-12-10T09:43:29Z'
reason: Previous GHCID with incorrect region code
- ghcid: JP-AK-KAZ-M-OSCC
ghcid_numeric: 13434133056760519923
valid_from: '2025-12-06T23:38:31.078680+00:00'
@ -101,8 +102,8 @@ ch_annotator:
annotation_metadata:
confidence_score: 0.98
verified: false
verification_date:
verified_by:
verification_date: null
verified_by: null
entity_claims:
- claim_type: full_name
claim_value: OYU STONE CIRCLE CENTER
@ -200,7 +201,7 @@ wikidata_enrichment:
location:
city: Kazuno Shi
region: Akita Ken
region_code: 05
region_code: 5
country: JP
postal_code: 018-5421
street_address: TOWADA OYU, Kazuno Shi, Akita Ken, 018-5421
@ -215,3 +216,36 @@ location:
geonames_id: 11612632
geonames_name: Kazuno
feature_code: PPLA2
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:31:36.815238+00:00'
source_url: https://www.city.kazuno.akita.jp/kanko_bunka_sports/bunkazai/7/5593.html
extraction_method: crawl4ai
claims:
- claim_type: logo_url
claim_value: https://www.city.kazuno.lg.jp/theme/base/img_common/pc_header_logo.png
source_url: https://www.city.kazuno.akita.jp/kanko_bunka_sports/bunkazai/7/5593.html
css_selector: '#header-logo > a > img'
retrieved_on: '2025-12-23T16:31:36.815238+00:00'
extraction_method: crawl4ai_header_logo
detection_confidence: high
alt_text: 鹿角市(かづのし)世界遺産のまち
- claim_type: favicon_url
claim_value: https://www.city.kazuno.lg.jp/theme/base/img_common/smartphone.png
source_url: https://www.city.kazuno.akita.jp/kanko_bunka_sports/bunkazai/7/5593.html
css_selector: '[document] > html > head > link:nth-of-type(3)'
retrieved_on: '2025-12-23T16:31:36.815238+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
- claim_type: og_image_url
claim_value: https://www.city.kazuno.lg.jp/theme/base/img_common/ogp_noimage.png
source_url: https://www.city.kazuno.akita.jp/kanko_bunka_sports/bunkazai/7/5593.html
css_selector: '[document] > html > head > meta:nth-of-type(7)'
retrieved_on: '2025-12-23T16:31:36.815238+00:00'
extraction_method: crawl4ai_meta_og
summary:
total_claims: 3
has_primary_logo: true
has_favicon: true
has_og_image: true
favicon_count: 2

View file

@ -205,3 +205,28 @@ wikidata_enrichment:
wikidata_web:
official_website: http://www.city.kitaakita.akita.jp/koukyoushisetu/bunka_hukushi/tosyokan/
wikidata_official_website: http://www.city.kitaakita.akita.jp/koukyoushisetu/bunka_hukushi/tosyokan/
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:31:46.454355+00:00'
source_url: http://www.city.kitaakita.akita.jp/koukyoushisetu/bunka_hukushi/tosyokan
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: https://www.city.kitaakita.akita.jp/assets/front/img/apple-touch-icon.png
source_url: http://www.city.kitaakita.akita.jp/koukyoushisetu/bunka_hukushi/tosyokan
css_selector: '[document] > html > head > link'
retrieved_on: '2025-12-23T16:31:46.454355+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
- claim_type: og_image_url
claim_value: https://www.city.kitaakita.akita.jp/uploads/common/og.png
source_url: http://www.city.kitaakita.akita.jp/koukyoushisetu/bunka_hukushi/tosyokan
css_selector: '[document] > html > head > meta:nth-of-type(9)'
retrieved_on: '2025-12-23T16:31:46.454355+00:00'
extraction_method: crawl4ai_meta_og
summary:
total_claims: 2
has_primary_logo: false
has_favicon: true
has_og_image: true
favicon_count: 1

View file

@ -205,3 +205,28 @@ wikidata_enrichment:
wikidata_web:
official_website: http://www.city.kitaakita.akita.jp/koukyoushisetu/bunka_hukushi/tosyokan/
wikidata_official_website: http://www.city.kitaakita.akita.jp/koukyoushisetu/bunka_hukushi/tosyokan/
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:31:55.240922+00:00'
source_url: http://www.city.kitaakita.akita.jp/koukyoushisetu/bunka_hukushi/tosyokan
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: https://www.city.kitaakita.akita.jp/assets/front/img/apple-touch-icon.png
source_url: http://www.city.kitaakita.akita.jp/koukyoushisetu/bunka_hukushi/tosyokan
css_selector: '[document] > html > head > link'
retrieved_on: '2025-12-23T16:31:55.240922+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
- claim_type: og_image_url
claim_value: https://www.city.kitaakita.akita.jp/uploads/common/og.png
source_url: http://www.city.kitaakita.akita.jp/koukyoushisetu/bunka_hukushi/tosyokan
css_selector: '[document] > html > head > meta:nth-of-type(9)'
retrieved_on: '2025-12-23T16:31:55.240922+00:00'
extraction_method: crawl4ai_meta_og
summary:
total_claims: 2
has_primary_logo: false
has_favicon: true
has_og_image: true
favicon_count: 1

View file

@ -202,3 +202,31 @@ wikidata_enrichment:
wikidata_web:
official_website: https://www.vill.kamikoani.akita.jp/forms/div/divinfolist.aspx?div_id=175
wikidata_official_website: https://www.vill.kamikoani.akita.jp/forms/div/divinfolist.aspx?div_id=175
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:32:03.826483+00:00'
source_url: https://www.vill.kamikoani.akita.jp/forms/div/divinfolist.aspx?div_id=175
extraction_method: crawl4ai
claims:
- claim_type: logo_url
claim_value: https://www.vill.kamikoani.akita.jp/div/admin/image/logo/header/logo.png
source_url: https://www.vill.kamikoani.akita.jp/forms/div/divinfolist.aspx?div_id=175
css_selector: '[document] > html > body.fontchangetarget > form > header.header
> div.navbar.container > div.navbar__logo2 > a > img'
retrieved_on: '2025-12-23T16:32:03.826483+00:00'
extraction_method: crawl4ai_header_logo
detection_confidence: high
alt_text: 上小阿仁村
- claim_type: favicon_url
claim_value: https://www.vill.kamikoani.akita.jp/div/admin/image/icon/favicon/favicon.ico
source_url: https://www.vill.kamikoani.akita.jp/forms/div/divinfolist.aspx?div_id=175
css_selector: '[document] > html > head > link:nth-of-type(37)'
retrieved_on: '2025-12-23T16:32:03.826483+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
summary:
total_claims: 2
has_primary_logo: true
has_favicon: true
has_og_image: false
favicon_count: 1

View file

@ -205,3 +205,28 @@ wikidata_enrichment:
wikidata_web:
official_website: http://www.city.kitaakita.akita.jp/koukyoushisetu/bunka_hukushi/tosyokan/index.html
wikidata_official_website: http://www.city.kitaakita.akita.jp/koukyoushisetu/bunka_hukushi/tosyokan/index.html
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:32:12.834770+00:00'
source_url: http://www.city.kitaakita.akita.jp/koukyoushisetu/bunka_hukushi/tosyokan/index.html
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: https://www.city.kitaakita.akita.jp/assets/front/img/apple-touch-icon.png
source_url: http://www.city.kitaakita.akita.jp/koukyoushisetu/bunka_hukushi/tosyokan/index.html
css_selector: '[document] > html > head > link'
retrieved_on: '2025-12-23T16:32:12.834770+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
- claim_type: og_image_url
claim_value: https://www.city.kitaakita.akita.jp/uploads/common/og.png
source_url: http://www.city.kitaakita.akita.jp/koukyoushisetu/bunka_hukushi/tosyokan/index.html
css_selector: '[document] > html > head > meta:nth-of-type(9)'
retrieved_on: '2025-12-23T16:32:12.834770+00:00'
extraction_method: crawl4ai_meta_og
summary:
total_claims: 2
has_primary_logo: false
has_favicon: true
has_og_image: true
favicon_count: 1

View file

@ -205,3 +205,28 @@ wikidata_enrichment:
wikidata_web:
official_website: http://www.city.kitaakita.akita.jp/koukyoushisetu/bunka_hukushi/tosyokan/library.html
wikidata_official_website: http://www.city.kitaakita.akita.jp/koukyoushisetu/bunka_hukushi/tosyokan/library.html
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:32:21.943314+00:00'
source_url: http://www.city.kitaakita.akita.jp/koukyoushisetu/bunka_hukushi/tosyokan/library.html
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: https://www.city.kitaakita.akita.jp/assets/front/img/apple-touch-icon.png
source_url: http://www.city.kitaakita.akita.jp/koukyoushisetu/bunka_hukushi/tosyokan/library.html
css_selector: '[document] > html > head > link'
retrieved_on: '2025-12-23T16:32:21.943314+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
- claim_type: og_image_url
claim_value: https://www.city.kitaakita.akita.jp/uploads/common/og.png
source_url: http://www.city.kitaakita.akita.jp/koukyoushisetu/bunka_hukushi/tosyokan/library.html
css_selector: '[document] > html > head > meta:nth-of-type(9)'
retrieved_on: '2025-12-23T16:32:21.943314+00:00'
extraction_method: crawl4ai_meta_og
summary:
total_claims: 2
has_primary_logo: false
has_favicon: true
has_og_image: true
favicon_count: 1

View file

@ -1155,3 +1155,36 @@ youtube_enrichment:
comments: []
thumbnail_url: https://i.ytimg.com/vi/AhvXckvWS94/hqdefault.jpg
status: SUCCESS
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:32:42.286885+00:00'
source_url: http://hahaha.akita.jp/wp/kumakuma
extraction_method: crawl4ai
claims:
- claim_type: logo_url
claim_value: http://hahaha.akita.jp/wp/kumakuma/wp-content/uploads/2020/05/logokuma.png
source_url: http://hahaha.akita.jp/wp/kumakuma
css_selector: '#logo > a > img'
retrieved_on: '2025-12-23T16:32:42.286885+00:00'
extraction_method: crawl4ai_header_logo
detection_confidence: high
alt_text: くまくま園 公式ホームページ
- claim_type: favicon_url
claim_value: http://hahaha.akita.jp/wp/kumakuma/wp-content/uploads/2019/04/cropped-DSF5649-180x180.jpg
source_url: http://hahaha.akita.jp/wp/kumakuma
css_selector: '[document] > html.no-js > head > link:nth-of-type(27)'
retrieved_on: '2025-12-23T16:32:42.286885+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
- claim_type: og_image_url
claim_value: http://hahaha.akita.jp/wp/kumakuma/wp-content/uploads/2019/04/7218.jpg
source_url: http://hahaha.akita.jp/wp/kumakuma
css_selector: '[document] > html.no-js > head > meta:nth-of-type(14)'
retrieved_on: '2025-12-23T16:32:42.286885+00:00'
extraction_method: crawl4ai_meta_og
summary:
total_claims: 3
has_primary_logo: true
has_favicon: true
has_og_image: true
favicon_count: 3

View file

@ -720,3 +720,22 @@ youtube_enrichment:
comments: []
thumbnail_url: https://i.ytimg.com/vi/uGw13ovqmI4/hqdefault.jpg
status: SUCCESS
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:32:54.969217+00:00'
source_url: https://www.kumakogen.jp/site/muse
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: https://www.kumakogen.jp/apple-touch-icon.png
source_url: https://www.kumakogen.jp/site/muse
css_selector: '[document] > html > head > link:nth-of-type(5)'
retrieved_on: '2025-12-23T16:32:54.969217+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
summary:
total_claims: 1
has_primary_logo: false
has_favicon: true
has_og_image: false
favicon_count: 3

View file

@ -243,3 +243,28 @@ location:
geonames_id: 1926100
feature_code: PPL
normalization_timestamp: '2025-12-09T06:53:26.596703+00:00'
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:33:17.535887+00:00'
source_url: http://www.morinokuni.or.jp
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: http://www.morinokuni.or.jp/files/favicon/favicon.ico?cache=20251224013253
source_url: http://www.morinokuni.or.jp
css_selector: '[document] > html > head > link:nth-of-type(15)'
retrieved_on: '2025-12-23T16:33:17.535887+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
- claim_type: og_image_url
claim_value: https://morinokuni.or.jp/css/public/pc/image/ogimage.jpg
source_url: http://www.morinokuni.or.jp
css_selector: '[document] > html > head > meta:nth-of-type(13)'
retrieved_on: '2025-12-23T16:33:17.535887+00:00'
extraction_method: crawl4ai_meta_og
summary:
total_claims: 2
has_primary_logo: false
has_favicon: true
has_og_image: true
favicon_count: 1

View file

@ -369,3 +369,28 @@ location:
geonames_id: 1926099
feature_code: PPLA
normalization_timestamp: '2025-12-09T06:53:26.660999+00:00'
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:33:27.766117+00:00'
source_url: https://www.ehime-u.ac.jp/about/ehime-u-museum
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: https://www.ehime-u.ac.jp/wp-content/themes/ehime-university/assets/images/favicons/apple-touch-icon-180x180.png
source_url: https://www.ehime-u.ac.jp/about/ehime-u-museum
css_selector: '[document] > html > head > link:nth-of-type(11)'
retrieved_on: '2025-12-23T16:33:27.766117+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: 180x180
- claim_type: og_image_url
claim_value: https://www.ehime-u.ac.jp/wp-content/uploads/2022/03/愛媛大学ミュージアム外観.jpg
source_url: https://www.ehime-u.ac.jp/about/ehime-u-museum
css_selector: '[document] > html > head > meta:nth-of-type(15)'
retrieved_on: '2025-12-23T16:33:27.766117+00:00'
extraction_method: crawl4ai_meta_og
summary:
total_claims: 2
has_primary_logo: false
has_favicon: true
has_og_image: true
favicon_count: 39

View file

@ -207,3 +207,22 @@ location:
geonames_id: 1854678
geonames_name: Ōgata
feature_code: PPL
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:33:36.471637+00:00'
source_url: https://libwww.akita-pu.ac.jp/drupal
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: https://libwww.akita-pu.ac.jp/opac/images/cyan/favicon.ico
source_url: https://libwww.akita-pu.ac.jp/drupal
css_selector: '[document] > html > head > link:nth-of-type(9)'
retrieved_on: '2025-12-23T16:33:36.471637+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: image/x-icon
favicon_sizes: ''
summary:
total_claims: 1
has_primary_logo: false
has_favicon: true
has_og_image: false
favicon_count: 1

View file

@ -200,3 +200,36 @@ wikidata_enrichment:
wikidata_web:
official_website: http://www.town.hachirogata.akita.jp/g.html?seq=107
wikidata_official_website: http://www.town.hachirogata.akita.jp/g.html?seq=107
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:33:48.329312+00:00'
source_url: http://www.town.hachirogata.akita.jp/g.html?seq=107
extraction_method: crawl4ai
claims:
- claim_type: logo_url
claim_value: http://www.town.hachirogata.akita.jp/_template_/_site_/_default_/_res/design/images/header/hachirogata_logo.png
source_url: http://www.town.hachirogata.akita.jp/g.html?seq=107
css_selector: '#tlogo > h1 > a > img'
retrieved_on: '2025-12-23T16:33:48.329312+00:00'
extraction_method: crawl4ai_header_logo
detection_confidence: high
alt_text: 八郎潟町公式サイトトップページ
- claim_type: favicon_url
claim_value: http://www.town.hachirogata.akita.jp/_template_/_site_/_default_/_res/images/apple-touch-icon-precomposed_.png
source_url: http://www.town.hachirogata.akita.jp/g.html?seq=107
css_selector: '[document] > html > head > link:nth-of-type(5)'
retrieved_on: '2025-12-23T16:33:48.329312+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
- claim_type: og_image_url
claim_value: https://www.town.hachirogata.akita.jp/_template_/_site_/_default_/_res/images/sns/ogimage_.png
source_url: http://www.town.hachirogata.akita.jp/g.html?seq=107
css_selector: '[document] > html > head > meta:nth-of-type(9)'
retrieved_on: '2025-12-23T16:33:48.329312+00:00'
extraction_method: crawl4ai_meta_og
summary:
total_claims: 3
has_primary_logo: true
has_favicon: true
has_og_image: true
favicon_count: 2

View file

@ -403,3 +403,30 @@ location:
geonames_id: 1926087
feature_code: PPL
normalization_timestamp: '2025-12-09T06:53:26.728705+00:00'
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:34:05.716767+00:00'
source_url: https://www.city.imabari.ehime.jp/museum/omishima
extraction_method: crawl4ai
claims:
- claim_type: logo_url
claim_value: https://www.city.imabari.ehime.jp/museum/omishima/img/logo.gif
source_url: https://www.city.imabari.ehime.jp/museum/omishima
css_selector: '#museum_logo > a > img'
retrieved_on: '2025-12-23T16:34:05.716767+00:00'
extraction_method: crawl4ai_header_logo
detection_confidence: high
alt_text: 大三島美術館
- claim_type: favicon_url
claim_value: https://www.city.imabari.ehime.jp/museum/favicon.ico
source_url: https://www.city.imabari.ehime.jp/museum/omishima
css_selector: '[document] > html > head > link:nth-of-type(4)'
retrieved_on: '2025-12-23T16:34:05.716767+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
summary:
total_claims: 2
has_primary_logo: true
has_favicon: true
has_og_image: false
favicon_count: 1

View file

@ -204,3 +204,36 @@ wikidata_enrichment:
wikidata_web:
official_website: http://www.city.nikaho.akita.jp/life/detail.html?id=201
wikidata_official_website: http://www.city.nikaho.akita.jp/life/detail.html?id=201
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:34:17.852076+00:00'
source_url: http://www.city.nikaho.akita.jp/life/detail.html?id=201
extraction_method: crawl4ai
claims:
- claim_type: logo_url
claim_value: http://www.city.nikaho.akita.jp/theme/base/s-admin/img_top/pc_header_logo.png
source_url: http://www.city.nikaho.akita.jp/life/detail.html?id=201
css_selector: '#sp-header > div.box.clearfix > a > img.header-logo'
retrieved_on: '2025-12-23T16:34:17.852076+00:00'
extraction_method: crawl4ai_header_logo
detection_confidence: high
alt_text: にかほ市
- claim_type: favicon_url
claim_value: http://www.city.nikaho.akita.jp/theme/base/img_common/smartphone.png
source_url: http://www.city.nikaho.akita.jp/life/detail.html?id=201
css_selector: '[document] > html > head > link:nth-of-type(3)'
retrieved_on: '2025-12-23T16:34:17.852076+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
- claim_type: og_image_url
claim_value: http://www.city.nikaho.akita.jp/theme/base/img_common/ogp_noimage.png
source_url: http://www.city.nikaho.akita.jp/life/detail.html?id=201
css_selector: '[document] > html > head > meta:nth-of-type(8)'
retrieved_on: '2025-12-23T16:34:17.852076+00:00'
extraction_method: crawl4ai_meta_og
summary:
total_claims: 3
has_primary_logo: true
has_favicon: true
has_og_image: true
favicon_count: 2

View file

@ -207,3 +207,36 @@ wikidata_enrichment:
wikidata_web:
official_website: http://www.city.nikaho.akita.jp/life/detail.html?id=201
wikidata_official_website: http://www.city.nikaho.akita.jp/life/detail.html?id=201
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:34:26.027443+00:00'
source_url: http://www.city.nikaho.akita.jp/life/detail.html?id=201
extraction_method: crawl4ai
claims:
- claim_type: logo_url
claim_value: http://www.city.nikaho.akita.jp/theme/base/s-admin/img_top/pc_header_logo.png
source_url: http://www.city.nikaho.akita.jp/life/detail.html?id=201
css_selector: '#sp-header > div.box.clearfix > a > img.header-logo'
retrieved_on: '2025-12-23T16:34:26.027443+00:00'
extraction_method: crawl4ai_header_logo
detection_confidence: high
alt_text: にかほ市
- claim_type: favicon_url
claim_value: http://www.city.nikaho.akita.jp/theme/base/img_common/smartphone.png
source_url: http://www.city.nikaho.akita.jp/life/detail.html?id=201
css_selector: '[document] > html > head > link:nth-of-type(3)'
retrieved_on: '2025-12-23T16:34:26.027443+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
- claim_type: og_image_url
claim_value: http://www.city.nikaho.akita.jp/theme/base/img_common/ogp_noimage.png
source_url: http://www.city.nikaho.akita.jp/life/detail.html?id=201
css_selector: '[document] > html > head > meta:nth-of-type(8)'
retrieved_on: '2025-12-23T16:34:26.027443+00:00'
extraction_method: crawl4ai_meta_og
summary:
total_claims: 3
has_primary_logo: true
has_favicon: true
has_og_image: true
favicon_count: 2

View file

@ -32,18 +32,19 @@ ghcid:
generation_timestamp: '2025-12-06T23:38:31.121722+00:00'
location_resolution:
country_code: JP
region_code: 05
region_code: 5
city_code: NIK
method: CH_ANNOTATOR_SOURCE
ghcid_history:
- ghcid: JP-05-NIK-M-KM
valid_from: "2025-12-10T09:43:29Z"
valid_from: '2025-12-10T09:43:29Z'
valid_to: null
reason: "Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO 3166-2:JP"
reason: Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO
3166-2:JP
- ghcid: JP-AK-NIK-M-KM
valid_from: null
valid_to: "2025-12-10T09:43:29Z"
reason: "Previous GHCID with incorrect region code"
valid_to: '2025-12-10T09:43:29Z'
reason: Previous GHCID with incorrect region code
- ghcid: JP-AK-NIK-M-KM
ghcid_numeric: 5835839064655281895
valid_from: '2025-12-06T23:38:31.121722+00:00'
@ -101,8 +102,8 @@ ch_annotator:
annotation_metadata:
confidence_score: 0.98
verified: false
verification_date:
verified_by:
verification_date: null
verified_by: null
entity_claims:
- claim_type: full_name
claim_value: KISAKATA MUSEUM
@ -171,8 +172,8 @@ wikidata_enrichment:
instance_of: &id004
- id: Q33506
label: museum
description: institution that holds artifacts and other objects of scientific, artistic, cultural, historical, or other
importance
description: institution that holds artifacts and other objects of scientific,
artistic, cultural, historical, or other importance
wikidata_instance_of: *id004
wikidata_location:
country: &id005
@ -196,7 +197,7 @@ wikidata_enrichment:
location:
city: Nikaho Shi
region: Akita Ken
region_code: 05
region_code: 5
country: JP
postal_code: 018-0104
street_address: KISAKATAMACHI KITSUNEMORI, Nikaho Shi, Akita Ken, 018-0104
@ -211,3 +212,36 @@ location:
geonames_id: 6822198
geonames_name: Nikaho
feature_code: PPLA2
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:34:44.950203+00:00'
source_url: https://www.city.nikaho.akita.jp/life/detail.html?id=210
extraction_method: crawl4ai
claims:
- claim_type: logo_url
claim_value: https://www.city.nikaho.akita.jp/theme/base/s-admin/img_top/pc_header_logo.png
source_url: https://www.city.nikaho.akita.jp/life/detail.html?id=210
css_selector: '#sp-header > div.box.clearfix > a > img.header-logo'
retrieved_on: '2025-12-23T16:34:44.950203+00:00'
extraction_method: crawl4ai_header_logo
detection_confidence: high
alt_text: にかほ市
- claim_type: favicon_url
claim_value: https://www.city.nikaho.akita.jp/theme/base/img_common/smartphone.png
source_url: https://www.city.nikaho.akita.jp/life/detail.html?id=210
css_selector: '[document] > html > head > link:nth-of-type(3)'
retrieved_on: '2025-12-23T16:34:44.950203+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
- claim_type: og_image_url
claim_value: https://www.city.nikaho.akita.jp/theme/base/img_common/ogp_noimage.png
source_url: https://www.city.nikaho.akita.jp/life/detail.html?id=210
css_selector: '[document] > html > head > meta:nth-of-type(8)'
retrieved_on: '2025-12-23T16:34:44.950203+00:00'
extraction_method: crawl4ai_meta_og
summary:
total_claims: 3
has_primary_logo: true
has_favicon: true
has_og_image: true
favicon_count: 2

View file

@ -34,18 +34,19 @@ ghcid:
generation_timestamp: '2025-12-06T23:38:31.131423+00:00'
location_resolution:
country_code: JP
region_code: 05
region_code: 5
city_code: NIK
method: CH_ANNOTATOR_SOURCE
ghcid_history:
- ghcid: JP-05-NIK-M-TM
valid_from: "2025-12-10T09:43:29Z"
valid_from: '2025-12-10T09:43:29Z'
valid_to: null
reason: "Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO 3166-2:JP"
reason: Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO
3166-2:JP
- ghcid: JP-AK-NIK-M-TM
valid_from: null
valid_to: "2025-12-10T09:43:29Z"
reason: "Previous GHCID with incorrect region code"
valid_to: '2025-12-10T09:43:29Z'
reason: Previous GHCID with incorrect region code
- ghcid: JP-AK-NIK-M-TM
ghcid_numeric: 13141746719298254165
valid_from: '2025-12-06T23:38:31.131423+00:00'
@ -232,8 +233,33 @@ location:
source_path: wikidata_enrichment.wikidata_coordinates
city: Nikaho Shi
region: Akita Ken
region_code: 05
region_code: 5
country: *id005
postal_code: 018-0402
street_address: HIRASAWA, Nikaho Shi, Akita Ken, 018-0402
normalization_timestamp: '2025-12-09T10:55:22.600756+00:00'
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:34:59.980614+00:00'
source_url: https://www.tdk.com/museum
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: https://www.tdk.com/themes/custom/tdkcom/src/favicons/TDK_Favicon_180x180_BT.png
source_url: https://www.tdk.com/museum
css_selector: '[document] > html.no-touchevents.inputtypes-search > head > link:nth-of-type(9)'
retrieved_on: '2025-12-23T16:34:59.980614+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: 180x180
- claim_type: og_image_url
claim_value: https://www.tdk.com/system/files/dam/image/TDK_logo_blue_1200_630.png
source_url: https://www.tdk.com/museum
css_selector: '[document] > html.no-touchevents.inputtypes-search > head > meta:nth-of-type(6)'
retrieved_on: '2025-12-23T16:34:59.980614+00:00'
extraction_method: crawl4ai_meta_og
summary:
total_claims: 2
has_primary_logo: false
has_favicon: true
has_og_image: true
favicon_count: 6

View file

@ -241,3 +241,22 @@ location:
geonames_id: 1926070
feature_code: PPL
normalization_timestamp: '2025-12-09T06:53:26.783150+00:00'
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:35:31.879456+00:00'
source_url: https://www.city.saijo.ehime.jp/soshiki/syakaikyoiku/kyodo-index.html
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: https://www.city.saijo.ehime.jp/apple-touch-icon.png
source_url: https://www.city.saijo.ehime.jp/soshiki/syakaikyoiku/kyodo-index.html
css_selector: '[document] > html > head > link:nth-of-type(3)'
retrieved_on: '2025-12-23T16:35:31.879456+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
summary:
total_claims: 1
has_primary_logo: false
has_favicon: true
has_og_image: false
favicon_count: 2

View file

@ -32,18 +32,19 @@ ghcid:
generation_timestamp: '2025-12-06T23:38:54.486214+00:00'
location_resolution:
country_code: JP
region_code: 05
region_code: 5
city_code: ODA
method: CH_ANNOTATOR_SOURCE
ghcid_history:
- ghcid: JP-05-ODA-L-AL
valid_from: "2025-12-10T09:43:29Z"
valid_from: '2025-12-10T09:43:29Z'
valid_to: null
reason: "Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO 3166-2:JP"
reason: Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO
3166-2:JP
- ghcid: JP-AK-ODA-L-AL
valid_from: null
valid_to: "2025-12-10T09:43:29Z"
reason: "Previous GHCID with incorrect region code"
valid_to: '2025-12-10T09:43:29Z'
reason: Previous GHCID with incorrect region code
- ghcid: JP-AK-ODA-L-AL
ghcid_numeric: 1915600020121425453
valid_from: '2025-12-06T23:38:54.486214+00:00'
@ -101,8 +102,8 @@ ch_annotator:
annotation_metadata:
confidence_score: 0.98
verified: false
verification_date:
verified_by:
verification_date: null
verified_by: null
entity_claims:
- claim_type: full_name
claim_value: AKITAKANGOFUKUSHIDAIGAKUFUZOKU Library
@ -200,7 +201,7 @@ wikidata_enrichment:
location:
city: Odate Shi
region: Akita Ken
region_code: 05
region_code: 5
country: JP
postal_code: 017-0046
street_address: 2-3-4 SHIMIZU, Odate Shi, Akita Ken, 017-0046
@ -215,3 +216,22 @@ location:
geonames_id: 2128787
geonames_name: Ōdate
feature_code: PPLA2
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:35:43.736346+00:00'
source_url: http://www.well.ac.jp/library/index.html
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: https://www.well.ac.jp/assets/themes/custom/apple-touch-icon.png
source_url: http://www.well.ac.jp/library/index.html
css_selector: '[document] > html > head > link:nth-of-type(3)'
retrieved_on: '2025-12-23T16:35:43.736346+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
summary:
total_claims: 1
has_primary_logo: false
has_favicon: true
has_og_image: false
favicon_count: 2

View file

@ -204,3 +204,36 @@ wikidata_enrichment:
wikidata_media:
image: Oga City Library and Funakawako Community Centre.jpg
wikidata_image: Oga City Library and Funakawako Community Centre.jpg
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:36:29.058213+00:00'
source_url: http://www.city.oga.akita.jp/index.cfm/12
extraction_method: crawl4ai
claims:
- claim_type: logo_url
claim_value: http://www.city.oga.akita.jp/theme/base/img_common/pc_header_logo.png
source_url: http://www.city.oga.akita.jp/index.cfm/12
css_selector: '#header-logo > a > img'
retrieved_on: '2025-12-23T16:36:29.058213+00:00'
extraction_method: crawl4ai_header_logo
detection_confidence: high
alt_text: 男鹿市 OGA CITY
- claim_type: favicon_url
claim_value: http://www.city.oga.akita.jp/theme/base/img_common/smartphone.png
source_url: http://www.city.oga.akita.jp/index.cfm/12
css_selector: '[document] > html > head > link:nth-of-type(3)'
retrieved_on: '2025-12-23T16:36:29.058213+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
- claim_type: og_image_url
claim_value: http://www.city.oga.akita.jp/theme/base/img_common/ogp_noimage.png
source_url: http://www.city.oga.akita.jp/index.cfm/12
css_selector: '[document] > html > head > meta:nth-of-type(8)'
retrieved_on: '2025-12-23T16:36:29.058213+00:00'
extraction_method: crawl4ai_meta_og
summary:
total_claims: 3
has_primary_logo: true
has_favicon: true
has_og_image: true
favicon_count: 2

View file

@ -199,3 +199,36 @@ wikidata_enrichment:
wikidata_web:
official_website: http://www.city.oga.akita.jp/index.cfm/12
wikidata_official_website: http://www.city.oga.akita.jp/index.cfm/12
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:36:47.882466+00:00'
source_url: http://www.city.oga.akita.jp/index.cfm/12
extraction_method: crawl4ai
claims:
- claim_type: logo_url
claim_value: http://www.city.oga.akita.jp/theme/base/img_common/pc_header_logo.png
source_url: http://www.city.oga.akita.jp/index.cfm/12
css_selector: '#header-logo > a > img'
retrieved_on: '2025-12-23T16:36:47.882466+00:00'
extraction_method: crawl4ai_header_logo
detection_confidence: high
alt_text: 男鹿市 OGA CITY
- claim_type: favicon_url
claim_value: http://www.city.oga.akita.jp/theme/base/img_common/smartphone.png
source_url: http://www.city.oga.akita.jp/index.cfm/12
css_selector: '[document] > html > head > link:nth-of-type(3)'
retrieved_on: '2025-12-23T16:36:47.882466+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
- claim_type: og_image_url
claim_value: http://www.city.oga.akita.jp/theme/base/img_common/ogp_noimage.png
source_url: http://www.city.oga.akita.jp/index.cfm/12
css_selector: '[document] > html > head > meta:nth-of-type(8)'
retrieved_on: '2025-12-23T16:36:47.882466+00:00'
extraction_method: crawl4ai_meta_og
summary:
total_claims: 3
has_primary_logo: true
has_favicon: true
has_og_image: true
favicon_count: 2

View file

@ -223,3 +223,28 @@ wikidata_enrichment:
image: Entrance of Namahage Museum, Oga, Akita.JPG
commons_category: Namahage Museum
wikidata_image: Entrance of Namahage Museum, Oga, Akita.JPG
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:37:00.224317+00:00'
source_url: https://namahage.co.jp/namahagekan
extraction_method: crawl4ai
claims:
- claim_type: logo_url
claim_value: https://namahage.co.jp/namahagekan/img/logo.svg
source_url: https://namahage.co.jp/namahagekan
css_selector: '#logo > h1 > a > img'
retrieved_on: '2025-12-23T16:37:00.224317+00:00'
extraction_method: crawl4ai_header_logo
detection_confidence: high
alt_text: なまはげ館
- claim_type: og_image_url
claim_value: http://namahage.co.jp/namahagekan/img/og_image.jpg
source_url: https://namahage.co.jp/namahagekan
css_selector: '[document] > html > head > meta:nth-of-type(7)'
retrieved_on: '2025-12-23T16:37:00.224317+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

View file

@ -32,18 +32,19 @@ ghcid:
generation_timestamp: '2025-12-06T23:38:31.056462+00:00'
location_resolution:
country_code: JP
region_code: 05
region_code: 5
city_code: OGA
method: CH_ANNOTATOR_SOURCE
ghcid_history:
- ghcid: JP-05-OGA-M-OW
valid_from: "2025-12-10T09:43:29Z"
valid_from: '2025-12-10T09:43:29Z'
valid_to: null
reason: "Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO 3166-2:JP"
reason: Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO
3166-2:JP
- ghcid: JP-AK-OGA-M-OW
valid_from: null
valid_to: "2025-12-10T09:43:29Z"
reason: "Previous GHCID with incorrect region code"
valid_to: '2025-12-10T09:43:29Z'
reason: Previous GHCID with incorrect region code
- ghcid: JP-AK-OGA-M-OW
ghcid_numeric: 6360991033694890579
valid_from: '2025-12-06T23:38:31.056462+00:00'
@ -101,8 +102,8 @@ ch_annotator:
annotation_metadata:
confidence_score: 0.98
verified: false
verification_date:
verified_by:
verification_date: null
verified_by: null
entity_claims:
- claim_type: full_name
claim_value: OGASHI WAKAMIFURUSATOSHIRYOUKAN
@ -171,8 +172,8 @@ wikidata_enrichment:
instance_of: &id004
- id: Q33506
label: museum
description: institution that holds artifacts and other objects of scientific, artistic, cultural, historical, or other
importance
description: institution that holds artifacts and other objects of scientific,
artistic, cultural, historical, or other importance
wikidata_instance_of: *id004
wikidata_location:
country: &id005
@ -196,7 +197,7 @@ wikidata_enrichment:
location:
city: Oga Shi
region: Akita Ken
region_code: 05
region_code: 5
country: JP
postal_code: 010-0401
street_address: NOISHI, Oga Shi, Akita Ken, 010-0401
@ -211,3 +212,36 @@ location:
geonames_id: 6822201
geonames_name: Oga
feature_code: PPLA2
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:37:12.493621+00:00'
source_url: http://www.city.oga.akita.jp/index.cfm/14,1484,52,html
extraction_method: crawl4ai
claims:
- claim_type: logo_url
claim_value: http://www.city.oga.akita.jp/theme/base/img_common/pc_header_logo.png
source_url: http://www.city.oga.akita.jp/index.cfm/14,1484,52,html
css_selector: '#header-logo > a > img'
retrieved_on: '2025-12-23T16:37:12.493621+00:00'
extraction_method: crawl4ai_header_logo
detection_confidence: high
alt_text: 男鹿市 OGA CITY
- claim_type: favicon_url
claim_value: http://www.city.oga.akita.jp/theme/base/img_common/smartphone.png
source_url: http://www.city.oga.akita.jp/index.cfm/14,1484,52,html
css_selector: '[document] > html > head > link:nth-of-type(3)'
retrieved_on: '2025-12-23T16:37:12.493621+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
- claim_type: og_image_url
claim_value: http://www.city.oga.akita.jp/theme/base/img_common/ogp_noimage.png
source_url: http://www.city.oga.akita.jp/index.cfm/14,1484,52,html
css_selector: '[document] > html > head > meta:nth-of-type(8)'
retrieved_on: '2025-12-23T16:37:12.493621+00:00'
extraction_method: crawl4ai_meta_og
summary:
total_claims: 3
has_primary_logo: true
has_favicon: true
has_og_image: true
favicon_count: 2

View file

@ -204,3 +204,29 @@ wikidata_enrichment:
wikidata_web:
official_website: http://www.city.semboku.akita.jp/citizens/12_03.html
wikidata_official_website: http://www.city.semboku.akita.jp/citizens/12_03.html
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:37:39.177585+00:00'
source_url: http://www.city.semboku.akita.jp/citizens/12_03.html
extraction_method: crawl4ai
claims:
- claim_type: logo_url
claim_value: http://www.city.semboku.akita.jp/assets/img/common/logo_site.png
source_url: http://www.city.semboku.akita.jp/citizens/12_03.html
css_selector: '#top > header.header > div.header-inner.container > div.logo__btn__wrap
> div.header-logo > a > img'
retrieved_on: '2025-12-23T16:37:39.177585+00:00'
extraction_method: crawl4ai_header_logo
detection_confidence: high
alt_text: 仙北市
- claim_type: og_image_url
claim_value: https://www.city.semboku.akita.jp/ogp.jpg
source_url: http://www.city.semboku.akita.jp/citizens/12_03.html
css_selector: '[document] > html > head > meta:nth-of-type(9)'
retrieved_on: '2025-12-23T16:37:39.177585+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

View file

@ -244,3 +244,29 @@ wikidata_enrichment:
- id: Q11436810
label: Hiroshi Ōe
description: Japanese architect (1913-1989)
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:37:49.960825+00:00'
source_url: https://www.city.semboku.akita.jp/sightseeing/densyo
extraction_method: crawl4ai
claims:
- claim_type: logo_url
claim_value: https://www.city.semboku.akita.jp/assets/img/common/logo_site.png
source_url: https://www.city.semboku.akita.jp/sightseeing/densyo
css_selector: '#top > header.header > div.header-inner.container > div.logo__btn__wrap
> div.header-logo > a > img'
retrieved_on: '2025-12-23T16:37:49.960825+00:00'
extraction_method: crawl4ai_header_logo
detection_confidence: high
alt_text: 仙北市
- claim_type: og_image_url
claim_value: https://www.city.semboku.akita.jp/ogp.jpg
source_url: https://www.city.semboku.akita.jp/sightseeing/densyo
css_selector: '[document] > html > head > meta:nth-of-type(9)'
retrieved_on: '2025-12-23T16:37:49.960825+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

View file

@ -34,18 +34,19 @@ ghcid:
generation_timestamp: '2025-12-06T23:38:31.138776+00:00'
location_resolution:
country_code: JP
region_code: 05
region_code: 5
city_code: SEM
method: CH_ANNOTATOR_SOURCE
ghcid_history:
- ghcid: JP-05-SEM-M-OAM
valid_from: "2025-12-10T09:43:29Z"
valid_from: '2025-12-10T09:43:29Z'
valid_to: null
reason: "Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO 3166-2:JP"
reason: Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO
3166-2:JP
- ghcid: JP-AK-SEM-M-OAM
valid_from: null
valid_to: "2025-12-10T09:43:29Z"
reason: "Previous GHCID with incorrect region code"
valid_to: '2025-12-10T09:43:29Z'
reason: Previous GHCID with incorrect region code
- ghcid: JP-AK-SEM-M-OAM
ghcid_numeric: 3015213229431430773
valid_from: '2025-12-06T23:38:31.138776+00:00'
@ -242,8 +243,33 @@ location:
source_path: wikidata_enrichment.wikidata_coordinates
city: Semboku Shi
region: Akita Ken
region_code: 05
region_code: 5
country: *id006
postal_code: 014-0326
street_address: KAKUNODATEMACHI YAMANEMACHI, Semboku Shi, Akita Ken, 014-0326
normalization_timestamp: '2025-12-09T10:55:23.214529+00:00'
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:57:02.350663+00:00'
source_url: https://www.museomura.com
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: https://static.wixstatic.com/media/9baae4_94da8f8b5eb44a29bf8956317f0679d4%7Emv2.jpg/v1/fill/w_180%2Ch_180%2Clg_1%2Cusm_0.66_1.00_0.01/9baae4_94da8f8b5eb44a29bf8956317f0679d4%7Emv2.jpg
source_url: https://www.museomura.com
css_selector: '[document] > html > head > link:nth-of-type(3)'
retrieved_on: '2025-12-23T16:57:02.350663+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: image/jpeg
favicon_sizes: ''
- claim_type: og_image_url
claim_value: https://static.wixstatic.com/media/9baae4_8fe18281c0d84ad8ba9151372a14569c~mv2.jpg/v1/fill/w_2500,h_951,al_c/9baae4_8fe18281c0d84ad8ba9151372a14569c~mv2.jpg
source_url: https://www.museomura.com
css_selector: '[document] > html > head > meta:nth-of-type(14)'
retrieved_on: '2025-12-23T16:57:02.350663+00:00'
extraction_method: crawl4ai_meta_og
summary:
total_claims: 2
has_primary_logo: false
has_favicon: true
has_og_image: true
favicon_count: 3

View file

@ -379,3 +379,30 @@ location:
geonames_id: 8626922
feature_code: PPL
normalization_timestamp: '2025-12-09T06:53:26.980178+00:00'
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:58:06.626526+00:00'
source_url: https://www.city.imabari.ehime.jp/museum/tamagawa
extraction_method: crawl4ai
claims:
- claim_type: logo_url
claim_value: https://www.city.imabari.ehime.jp/museum/tamagawa/img/logo.gif
source_url: https://www.city.imabari.ehime.jp/museum/tamagawa
css_selector: '#museum_logo > a > img'
retrieved_on: '2025-12-23T16:58:06.626526+00:00'
extraction_method: crawl4ai_header_logo
detection_confidence: high
alt_text: 玉川近代美術館
- claim_type: favicon_url
claim_value: https://www.city.imabari.ehime.jp/museum/favicon.ico
source_url: https://www.city.imabari.ehime.jp/museum/tamagawa
css_selector: '[document] > html > head > link:nth-of-type(4)'
retrieved_on: '2025-12-23T16:58:06.626526+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
summary:
total_claims: 2
has_primary_logo: true
has_favicon: true
has_og_image: false
favicon_count: 1

View file

@ -381,3 +381,22 @@ location:
geonames_id: 1926020
feature_code: PPLA2
normalization_timestamp: '2025-12-09T06:53:27.085239+00:00'
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:58:14.746964+00:00'
source_url: https://www.city.uwajima.ehime.jp/site/siryoukan/rekishitop.html
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: https://www.city.uwajima.ehime.jp/apple-touch-icon.png
source_url: https://www.city.uwajima.ehime.jp/site/siryoukan/rekishitop.html
css_selector: '[document] > html > head > link:nth-of-type(3)'
retrieved_on: '2025-12-23T16:58:14.746964+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
summary:
total_claims: 1
has_primary_logo: false
has_favicon: true
has_og_image: false
favicon_count: 2

View file

@ -203,3 +203,30 @@ wikidata_enrichment:
wikidata_web:
official_website: http://www.town.fujisato.akita.jp/c.html?seq=85
wikidata_official_website: http://www.town.fujisato.akita.jp/c.html?seq=85
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:58:25.203841+00:00'
source_url: http://www.town.fujisato.akita.jp/c.html?seq=85
extraction_method: crawl4ai
claims:
- claim_type: logo_url
claim_value: http://www.town.fujisato.akita.jp/up/images/fujisato/image/logo.png
source_url: http://www.town.fujisato.akita.jp/c.html?seq=85
css_selector: '#logo > a.home > img.common'
retrieved_on: '2025-12-23T16:58:25.203841+00:00'
extraction_method: crawl4ai_header_logo
detection_confidence: high
alt_text: 藤里町
- claim_type: favicon_url
claim_value: http://www.town.fujisato.akita.jp/favicon.ico
source_url: http://www.town.fujisato.akita.jp/c.html?seq=85
css_selector: '[document] > html > head > link'
retrieved_on: '2025-12-23T16:58:25.203841+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

View file

@ -203,3 +203,28 @@ wikidata_enrichment:
- http://www.city.yokote.lg.jp/sub01/cat100168.html
- https://www.city.yokote.lg.jp/shisetsu/1001527/1004013.html
wikidata_official_website: *id006
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:58:48.498140+00:00'
source_url: http://www.city.yokote.lg.jp/sub01/cat100168.html
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: http://www.city.yokote.lg.jp/sub01/_template_/_site_/_default_/_res/images/apple-touch-icon-precomposed.png
source_url: http://www.city.yokote.lg.jp/sub01/cat100168.html
css_selector: '[document] > html > head > link:nth-of-type(5)'
retrieved_on: '2025-12-23T16:58:48.498140+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
- claim_type: og_image_url
claim_value: https://www.city.yokote.lg.jp/_template_/_site_/_default_/_res/images/sns/ogimage.png
source_url: http://www.city.yokote.lg.jp/sub01/cat100168.html
css_selector: '[document] > html > head > meta:nth-of-type(9)'
retrieved_on: '2025-12-23T16:58:48.498140+00:00'
extraction_method: crawl4ai_meta_og
summary:
total_claims: 2
has_primary_logo: false
has_favicon: true
has_og_image: true
favicon_count: 2

View file

@ -203,3 +203,36 @@ wikidata_enrichment:
- http://www.city.yokote.lg.jp/sub01/cat100168.html
- https://www.city.yokote.lg.jp/kurashi/1001140/1001251/1005858/1005936.html
wikidata_official_website: *id006
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:58:55.961999+00:00'
source_url: http://www.city.yokote.lg.jp/sub01/cat100168.html
extraction_method: crawl4ai
claims:
- claim_type: logo_url
claim_value: http://www.city.yokote.lg.jp/sub01/_template_/_site_/_default_/_res/design/images/header/yokote_logo2.png
source_url: http://www.city.yokote.lg.jp/sub01/cat100168.html
css_selector: '#logo2 > a > img'
retrieved_on: '2025-12-23T16:58:55.961999+00:00'
extraction_method: crawl4ai_header_logo
detection_confidence: high
alt_text: 横手市公式サイトトップページ
- claim_type: favicon_url
claim_value: http://www.city.yokote.lg.jp/sub01/_template_/_site_/_default_/_res/images/apple-touch-icon-precomposed.png
source_url: http://www.city.yokote.lg.jp/sub01/cat100168.html
css_selector: '[document] > html > head > link:nth-of-type(5)'
retrieved_on: '2025-12-23T16:58:55.961999+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
- claim_type: og_image_url
claim_value: https://www.city.yokote.lg.jp/_template_/_site_/_default_/_res/images/sns/ogimage.png
source_url: http://www.city.yokote.lg.jp/sub01/cat100168.html
css_selector: '[document] > html > head > meta:nth-of-type(9)'
retrieved_on: '2025-12-23T16:58:55.961999+00:00'
extraction_method: crawl4ai_meta_og
summary:
total_claims: 3
has_primary_logo: true
has_favicon: true
has_og_image: true
favicon_count: 2

View file

@ -225,3 +225,36 @@ wikidata_enrichment:
wikidata_web:
official_website: http://www.city.yokote.lg.jp/sub01/cat100168.html
wikidata_official_website: http://www.city.yokote.lg.jp/sub01/cat100168.html
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:59:07.532121+00:00'
source_url: http://www.city.yokote.lg.jp/sub01/cat100168.html
extraction_method: crawl4ai
claims:
- claim_type: logo_url
claim_value: http://www.city.yokote.lg.jp/sub01/_template_/_site_/_default_/_res/design/images/header/yokote_logo2.png
source_url: http://www.city.yokote.lg.jp/sub01/cat100168.html
css_selector: '#logo2 > a > img'
retrieved_on: '2025-12-23T16:59:07.532121+00:00'
extraction_method: crawl4ai_header_logo
detection_confidence: high
alt_text: 横手市公式サイトトップページ
- claim_type: favicon_url
claim_value: http://www.city.yokote.lg.jp/sub01/_template_/_site_/_default_/_res/images/apple-touch-icon-precomposed.png
source_url: http://www.city.yokote.lg.jp/sub01/cat100168.html
css_selector: '[document] > html > head > link:nth-of-type(5)'
retrieved_on: '2025-12-23T16:59:07.532121+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
- claim_type: og_image_url
claim_value: https://www.city.yokote.lg.jp/_template_/_site_/_default_/_res/images/sns/ogimage.png
source_url: http://www.city.yokote.lg.jp/sub01/cat100168.html
css_selector: '[document] > html > head > meta:nth-of-type(9)'
retrieved_on: '2025-12-23T16:59:07.532121+00:00'
extraction_method: crawl4ai_meta_og
summary:
total_claims: 3
has_primary_logo: true
has_favicon: true
has_og_image: true
favicon_count: 2

View file

@ -225,3 +225,36 @@ wikidata_enrichment:
wikidata_web:
official_website: http://www.city.yokote.lg.jp/sub01/cat100168.html
wikidata_official_website: http://www.city.yokote.lg.jp/sub01/cat100168.html
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:59:15.097221+00:00'
source_url: http://www.city.yokote.lg.jp/sub01/cat100168.html
extraction_method: crawl4ai
claims:
- claim_type: logo_url
claim_value: http://www.city.yokote.lg.jp/sub01/_template_/_site_/_default_/_res/design/images/header/yokote_logo2.png
source_url: http://www.city.yokote.lg.jp/sub01/cat100168.html
css_selector: '#logo2 > a > img'
retrieved_on: '2025-12-23T16:59:15.097221+00:00'
extraction_method: crawl4ai_header_logo
detection_confidence: high
alt_text: 横手市公式サイトトップページ
- claim_type: favicon_url
claim_value: http://www.city.yokote.lg.jp/sub01/_template_/_site_/_default_/_res/images/apple-touch-icon-precomposed.png
source_url: http://www.city.yokote.lg.jp/sub01/cat100168.html
css_selector: '[document] > html > head > link:nth-of-type(5)'
retrieved_on: '2025-12-23T16:59:15.097221+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
- claim_type: og_image_url
claim_value: https://www.city.yokote.lg.jp/_template_/_site_/_default_/_res/images/sns/ogimage.png
source_url: http://www.city.yokote.lg.jp/sub01/cat100168.html
css_selector: '[document] > html > head > meta:nth-of-type(9)'
retrieved_on: '2025-12-23T16:59:15.097221+00:00'
extraction_method: crawl4ai_meta_og
summary:
total_claims: 3
has_primary_logo: true
has_favicon: true
has_og_image: true
favicon_count: 2

View file

@ -229,3 +229,36 @@ wikidata_enrichment:
- http://www.city.yokote.lg.jp/sub01/cat100168.html
- https://www.city.yokote.lg.jp/kurashi/1001140/1001251/
wikidata_official_website: *id006
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:59:21.904895+00:00'
source_url: http://www.city.yokote.lg.jp/sub01/cat100168.html
extraction_method: crawl4ai
claims:
- claim_type: logo_url
claim_value: http://www.city.yokote.lg.jp/sub01/_template_/_site_/_default_/_res/design/images/header/yokote_logo2.png
source_url: http://www.city.yokote.lg.jp/sub01/cat100168.html
css_selector: '#logo2 > a > img'
retrieved_on: '2025-12-23T16:59:21.904895+00:00'
extraction_method: crawl4ai_header_logo
detection_confidence: high
alt_text: 横手市公式サイトトップページ
- claim_type: favicon_url
claim_value: http://www.city.yokote.lg.jp/sub01/_template_/_site_/_default_/_res/images/apple-touch-icon-precomposed.png
source_url: http://www.city.yokote.lg.jp/sub01/cat100168.html
css_selector: '[document] > html > head > link:nth-of-type(5)'
retrieved_on: '2025-12-23T16:59:21.904895+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
- claim_type: og_image_url
claim_value: https://www.city.yokote.lg.jp/_template_/_site_/_default_/_res/images/sns/ogimage.png
source_url: http://www.city.yokote.lg.jp/sub01/cat100168.html
css_selector: '[document] > html > head > meta:nth-of-type(9)'
retrieved_on: '2025-12-23T16:59:21.904895+00:00'
extraction_method: crawl4ai_meta_og
summary:
total_claims: 3
has_primary_logo: true
has_favicon: true
has_og_image: true
favicon_count: 2

View file

@ -232,3 +232,36 @@ wikidata_enrichment:
wikidata_media:
image: Yokote municipal Omonogawa library.jpg
wikidata_image: Yokote municipal Omonogawa library.jpg
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:59:29.674209+00:00'
source_url: http://www.city.yokote.lg.jp/sub01/cat100168.html
extraction_method: crawl4ai
claims:
- claim_type: logo_url
claim_value: http://www.city.yokote.lg.jp/sub01/_template_/_site_/_default_/_res/design/images/header/yokote_logo2.png
source_url: http://www.city.yokote.lg.jp/sub01/cat100168.html
css_selector: '#logo2 > a > img'
retrieved_on: '2025-12-23T16:59:29.674209+00:00'
extraction_method: crawl4ai_header_logo
detection_confidence: high
alt_text: 横手市公式サイトトップページ
- claim_type: favicon_url
claim_value: http://www.city.yokote.lg.jp/sub01/_template_/_site_/_default_/_res/images/apple-touch-icon-precomposed.png
source_url: http://www.city.yokote.lg.jp/sub01/cat100168.html
css_selector: '[document] > html > head > link:nth-of-type(5)'
retrieved_on: '2025-12-23T16:59:29.674209+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
- claim_type: og_image_url
claim_value: https://www.city.yokote.lg.jp/_template_/_site_/_default_/_res/images/sns/ogimage.png
source_url: http://www.city.yokote.lg.jp/sub01/cat100168.html
css_selector: '[document] > html > head > meta:nth-of-type(9)'
retrieved_on: '2025-12-23T16:59:29.674209+00:00'
extraction_method: crawl4ai_meta_og
summary:
total_claims: 3
has_primary_logo: true
has_favicon: true
has_og_image: true
favicon_count: 2

View file

@ -351,3 +351,41 @@ youtube_enrichment:
comments: []
thumbnail_url: https://i.ytimg.com/vi/20YO3JAXQ8A/hqdefault.jpg
status: SUCCESS
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:59:39.335966+00:00'
source_url: https://akitafurusatomura.co.jp
extraction_method: crawl4ai
claims:
- claim_type: logo_url
claim_value: https://akitafurusatomura.co.jp/wp-content/uploads/2023/11/header-logo.png
source_url: https://akitafurusatomura.co.jp
css_selector: '[document] > html.wf-a-otf-ud-shin-maru-go-pr6n-n3-active.wf-a-otf-ud-shin-go-pr6n-n3-active
> body.home.wp-singular > header.elementor.elementor-313 > header.elementor-element.elementor-element-f9ac638
> div.elementor-element.elementor-element-0d496d0 > div.elementor-element.elementor-element-f5d359b
> div.elementor-widget-container > a > img.attachment-full.size-full'
retrieved_on: '2025-12-23T16:59:39.335966+00:00'
extraction_method: crawl4ai_header_logo
detection_confidence: high
alt_text: ''
- claim_type: favicon_url
claim_value: https://akitafurusatomura.co.jp/wp-content/uploads/2023/11/akitafurusatomura-favicon-300x300.png
source_url: https://akitafurusatomura.co.jp
css_selector: '[document] > html.wf-a-otf-ud-shin-maru-go-pr6n-n3-active.wf-a-otf-ud-shin-go-pr6n-n3-active
> head > link:nth-of-type(57)'
retrieved_on: '2025-12-23T16:59:39.335966+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: 192x192
- claim_type: og_image_url
claim_value: https://akitafurusatomura.co.jp/wp-content/uploads/2025/08/yosakoi.jpg
source_url: https://akitafurusatomura.co.jp
css_selector: '[document] > html.wf-a-otf-ud-shin-maru-go-pr6n-n3-active.wf-a-otf-ud-shin-go-pr6n-n3-active
> head > meta:nth-of-type(13)'
retrieved_on: '2025-12-23T16:59:39.335966+00:00'
extraction_method: crawl4ai_meta_og
summary:
total_claims: 3
has_primary_logo: true
has_favicon: true
has_og_image: true
favicon_count: 2

View file

@ -32,18 +32,19 @@ ghcid:
generation_timestamp: '2025-12-06T23:38:31.037693+00:00'
location_resolution:
country_code: JP
region_code: 05
region_code: 5
city_code: YOK
method: CH_ANNOTATOR_SOURCE
ghcid_history:
- ghcid: JP-05-YOK-M-OLMH
valid_from: "2025-12-10T09:43:29Z"
valid_from: '2025-12-10T09:43:29Z'
valid_to: null
reason: "Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO 3166-2:JP"
reason: Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO
3166-2:JP
- ghcid: JP-AK-YOK-M-OLMH
valid_from: null
valid_to: "2025-12-10T09:43:29Z"
reason: "Previous GHCID with incorrect region code"
valid_to: '2025-12-10T09:43:29Z'
reason: Previous GHCID with incorrect region code
- ghcid: JP-AK-YOK-M-OLMH
ghcid_numeric: 14027401722154785391
valid_from: '2025-12-06T23:38:31.037693+00:00'
@ -101,8 +102,8 @@ ch_annotator:
annotation_metadata:
confidence_score: 0.98
verified: false
verification_date:
verified_by:
verification_date: null
verified_by: null
entity_claims:
- claim_type: full_name
claim_value: OMONOGAWA LOCAL MATERIAL HALL
@ -182,8 +183,8 @@ wikidata_enrichment:
instance_of: &id004
- id: Q33506
label: museum
description: institution that holds artifacts and other objects of scientific, artistic, cultural, historical, or other
importance
description: institution that holds artifacts and other objects of scientific,
artistic, cultural, historical, or other importance
wikidata_instance_of: *id004
wikidata_location:
country: &id005
@ -209,7 +210,7 @@ wikidata_enrichment:
location:
city: Yokote Shi
region: Akita Ken
region_code: 05
region_code: 5
country: JP
postal_code: 013-0208
street_address: OMONOGAWAMACHI NUMADATE, Yokote Shi, Akita Ken, 013-0208
@ -224,3 +225,28 @@ location:
geonames_id: 2110506
geonames_name: Yokote
feature_code: PPLA2
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:59:47.673944+00:00'
source_url: https://www.city.yokote.lg.jp
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: https://www.city.yokote.lg.jp/_template_/_site_/_default_/_res/images/apple-touch-icon-precomposed.png
source_url: https://www.city.yokote.lg.jp
css_selector: '[document] > html > head > link:nth-of-type(5)'
retrieved_on: '2025-12-23T16:59:47.673944+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
- claim_type: og_image_url
claim_value: https://www.city.yokote.lg.jp/_template_/_site_/_default_/_res/images/sns/ogimage.png
source_url: https://www.city.yokote.lg.jp
css_selector: '[document] > html > head > meta:nth-of-type(9)'
retrieved_on: '2025-12-23T16:59:47.673944+00:00'
extraction_method: crawl4ai_meta_og
summary:
total_claims: 2
has_primary_logo: false
has_favicon: true
has_og_image: true
favicon_count: 2

View file

@ -336,3 +336,22 @@ location:
geonames_id: 1926016
feature_code: PPL
normalization_timestamp: '2025-12-09T06:53:27.156836+00:00'
logo_enrichment:
enrichment_timestamp: '2025-12-23T16:59:55.061927+00:00'
source_url: https://www.city.toon.ehime.jp/soshiki/23/2431.html
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: https://www.city.toon.ehime.jp/img/icon/apple-touch-icon.png
source_url: https://www.city.toon.ehime.jp/soshiki/23/2431.html
css_selector: '[document] > html > head > link:nth-of-type(3)'
retrieved_on: '2025-12-23T16:59:55.061927+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
summary:
total_claims: 1
has_primary_logo: false
has_favicon: true
has_og_image: false
favicon_count: 2

View file

@ -229,3 +229,36 @@ wikidata_enrichment:
wikidata_media:
image: Ishizaka Yojiro Literature Museum.jpg
wikidata_image: Ishizaka Yojiro Literature Museum.jpg
logo_enrichment:
enrichment_timestamp: '2025-12-23T17:00:02.008254+00:00'
source_url: https://www.city.yokote.lg.jp/shogai/page000349.html
extraction_method: crawl4ai
claims:
- claim_type: logo_url
claim_value: https://www.city.yokote.lg.jp/shogai/_template_/_site_/_default_/_res/design/images/header/yokote_logo2.png
source_url: https://www.city.yokote.lg.jp/shogai/page000349.html
css_selector: '#logo2 > a > img'
retrieved_on: '2025-12-23T17:00:02.008254+00:00'
extraction_method: crawl4ai_header_logo
detection_confidence: high
alt_text: 横手市公式サイトトップページ
- claim_type: favicon_url
claim_value: https://www.city.yokote.lg.jp/shogai/_template_/_site_/_default_/_res/images/apple-touch-icon-precomposed.png
source_url: https://www.city.yokote.lg.jp/shogai/page000349.html
css_selector: '[document] > html > head > link:nth-of-type(5)'
retrieved_on: '2025-12-23T17:00:02.008254+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
- claim_type: og_image_url
claim_value: https://www.city.yokote.lg.jp/_template_/_site_/_default_/_res/images/sns/ogimage.png
source_url: https://www.city.yokote.lg.jp/shogai/page000349.html
css_selector: '[document] > html > head > meta:nth-of-type(9)'
retrieved_on: '2025-12-23T17:00:02.008254+00:00'
extraction_method: crawl4ai_meta_og
summary:
total_claims: 3
has_primary_logo: true
has_favicon: true
has_og_image: true
favicon_count: 2

View file

@ -242,3 +242,22 @@ wikidata_enrichment:
image: Yokote-Masuda Manga Museum 20190503.jpg
commons_category: Yokote-Masuda Manga Museum
wikidata_image: Yokote-Masuda Manga Museum 20190503.jpg
logo_enrichment:
enrichment_timestamp: '2025-12-23T17:00:11.269636+00:00'
source_url: https://manga-museum.com
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: https://manga-museum.com/wp-content/uploads/2019/02/favicon.ico
source_url: https://manga-museum.com
css_selector: '[document] > html.wf-inactive.wf-inactive > head > link:nth-of-type(22)'
retrieved_on: '2025-12-23T17:00:11.269636+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: 32x32
summary:
total_claims: 1
has_primary_logo: false
has_favicon: true
has_og_image: false
favicon_count: 1

View file

@ -32,18 +32,19 @@ ghcid:
generation_timestamp: '2025-12-06T23:38:53.911187+00:00'
location_resolution:
country_code: JP
region_code: 05
region_code: 5
city_code: YUR
method: CH_ANNOTATOR_SOURCE
ghcid_history:
- ghcid: JP-05-YUR-L-AH
valid_from: "2025-12-10T09:43:29Z"
valid_from: '2025-12-10T09:43:29Z'
valid_to: null
reason: "Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO 3166-2:JP"
reason: Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO
3166-2:JP
- ghcid: JP-AK-YUR-L-AH
valid_from: null
valid_to: "2025-12-10T09:43:29Z"
reason: "Previous GHCID with incorrect region code"
valid_to: '2025-12-10T09:43:29Z'
reason: Previous GHCID with incorrect region code
- ghcid: JP-AK-YUR-L-AH
ghcid_numeric: 14962919741502556453
valid_from: '2025-12-06T23:38:53.911187+00:00'
@ -101,8 +102,8 @@ ch_annotator:
annotation_metadata:
confidence_score: 0.98
verified: false
verification_date:
verified_by:
verification_date: null
verified_by: null
entity_claims:
- claim_type: full_name
claim_value: AKITAKENRITSUDAIGAKUTOSHOJOHOSENTA(HONJOKYAMPASU)
@ -189,7 +190,7 @@ wikidata_enrichment:
location:
city: Yurihonjo Shi
region: Akita Ken
region_code: 05
region_code: 5
country: JP
postal_code: 015-0055
street_address: 84-4 TSUCHIYA EBINOKUCHI, Yurihonjo Shi, Akita Ken, 015-0055
@ -204,3 +205,22 @@ location:
geonames_id: 6822202
geonames_name: Yurihonjō
feature_code: PPLA2
logo_enrichment:
enrichment_timestamp: '2025-12-23T17:00:22.961004+00:00'
source_url: https://libwww.akita-pu.ac.jp/drupal
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: https://libwww.akita-pu.ac.jp/opac/images/cyan/favicon.ico
source_url: https://libwww.akita-pu.ac.jp/drupal
css_selector: '[document] > html > head > link:nth-of-type(9)'
retrieved_on: '2025-12-23T17:00:22.961004+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: image/x-icon
favicon_sizes: ''
summary:
total_claims: 1
has_primary_logo: false
has_favicon: true
has_og_image: false
favicon_count: 1

View file

@ -32,18 +32,19 @@ ghcid:
generation_timestamp: '2025-12-06T23:38:31.081154+00:00'
location_resolution:
country_code: JP
region_code: 05
region_code: 5
city_code: YUR
method: CH_ANNOTATOR_SOURCE
ghcid_history:
- ghcid: JP-05-YUR-M-YMLMM
valid_from: "2025-12-10T09:43:29Z"
valid_from: '2025-12-10T09:43:29Z'
valid_to: null
reason: "Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO 3166-2:JP"
reason: Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO
3166-2:JP
- ghcid: JP-AK-YUR-M-YMLMM
valid_from: null
valid_to: "2025-12-10T09:43:29Z"
reason: "Previous GHCID with incorrect region code"
valid_to: '2025-12-10T09:43:29Z'
reason: Previous GHCID with incorrect region code
- ghcid: JP-AK-YUR-M-YMLMM
ghcid_numeric: 17602580394321561584
valid_from: '2025-12-06T23:38:31.081154+00:00'
@ -101,8 +102,8 @@ ch_annotator:
annotation_metadata:
confidence_score: 0.98
verified: false
verification_date:
verified_by:
verification_date: null
verified_by: null
entity_claims:
- claim_type: full_name
claim_value: YURIHONJO MUNICIPAL LOCAL MATERIAL MUSEUM
@ -207,7 +208,7 @@ wikidata_enrichment:
location:
city: Yurihonjo Shi
region: Akita Ken
region_code: 05
region_code: 5
country: JP
postal_code: 015-0011
street_address: ISHIWAKI, Yurihonjo Shi, Akita Ken, 015-0011
@ -222,3 +223,36 @@ location:
geonames_id: 6822202
geonames_name: Yurihonjō
feature_code: PPLA2
logo_enrichment:
enrichment_timestamp: '2025-12-23T17:05:02.539697+00:00'
source_url: https://www.city.yurihonjo.lg.jp/bunka-sport/bunka/c1323/5830
extraction_method: crawl4ai
claims:
- claim_type: logo_url
claim_value: https://www.city.yurihonjo.lg.jp/bunka-sport/bunka/c1323/_template_/_site_/_default_/_res/design/images/header/header-logo.png
source_url: https://www.city.yurihonjo.lg.jp/bunka-sport/bunka/c1323/5830
css_selector: '#tlogo > h1 > a > img'
retrieved_on: '2025-12-23T17:05:02.539697+00:00'
extraction_method: crawl4ai_header_logo
detection_confidence: high
alt_text: 由利本荘市公式サイトトップページ
- claim_type: favicon_url
claim_value: https://www.city.yurihonjo.lg.jp/bunka-sport/bunka/c1323/_template_/_site_/_default_/_res/images/apple-touch-icon.png?202406
source_url: https://www.city.yurihonjo.lg.jp/bunka-sport/bunka/c1323/5830
css_selector: '[document] > html > head > link:nth-of-type(5)'
retrieved_on: '2025-12-23T17:05:02.539697+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
- claim_type: og_image_url
claim_value: https://www.city.yurihonjo.lg.jp/_template_/_site_/_default_/_res/images/sns/ogimage.png
source_url: https://www.city.yurihonjo.lg.jp/bunka-sport/bunka/c1323/5830
css_selector: '[document] > html > head > meta:nth-of-type(11)'
retrieved_on: '2025-12-23T17:05:02.539697+00:00'
extraction_method: crawl4ai_meta_og
summary:
total_claims: 3
has_primary_logo: true
has_favicon: true
has_og_image: true
favicon_count: 2

View file

@ -205,3 +205,22 @@ wikidata_enrichment:
- http://www.city-yuzawa.jp/
- http://www.city-yuzawa.jp/shisetsu023/553
wikidata_official_website: *id006
logo_enrichment:
enrichment_timestamp: '2025-12-23T17:05:13.248293+00:00'
source_url: http://www.city-yuzawa.jp
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: http://www.city-yuzawa.jp/apple-touch-icon.png
source_url: http://www.city-yuzawa.jp
css_selector: '[document] > html > head > link:nth-of-type(3)'
retrieved_on: '2025-12-23T17:05:13.248293+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
summary:
total_claims: 1
has_primary_logo: false
has_favicon: true
has_og_image: false
favicon_count: 2

View file

@ -199,3 +199,22 @@ wikidata_enrichment:
wikidata_web:
official_website: http://www.city-yuzawa.jp
wikidata_official_website: http://www.city-yuzawa.jp
logo_enrichment:
enrichment_timestamp: '2025-12-23T17:05:18.929614+00:00'
source_url: http://www.city-yuzawa.jp
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: http://www.city-yuzawa.jp/apple-touch-icon.png
source_url: http://www.city-yuzawa.jp
css_selector: '[document] > html > head > link:nth-of-type(3)'
retrieved_on: '2025-12-23T17:05:18.929614+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
summary:
total_claims: 1
has_primary_logo: false
has_favicon: true
has_og_image: false
favicon_count: 2

View file

@ -199,3 +199,22 @@ wikidata_enrichment:
wikidata_web:
official_website: http://www.city-yuzawa.jp/shisetsu0422/index.html
wikidata_official_website: http://www.city-yuzawa.jp/shisetsu0422/index.html
logo_enrichment:
enrichment_timestamp: '2025-12-23T17:05:25.849672+00:00'
source_url: http://www.city-yuzawa.jp/shisetsu0422/index.html
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: http://www.city-yuzawa.jp/apple-touch-icon.png
source_url: http://www.city-yuzawa.jp/shisetsu0422/index.html
css_selector: '[document] > html > head > link:nth-of-type(3)'
retrieved_on: '2025-12-23T17:05:25.849672+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
summary:
total_claims: 1
has_primary_logo: false
has_favicon: true
has_og_image: false
favicon_count: 2

View file

@ -199,3 +199,22 @@ wikidata_enrichment:
wikidata_web:
official_website: http://www.city-yuzawa.jp/shisetsu0421/520.html
wikidata_official_website: http://www.city-yuzawa.jp/shisetsu0421/520.html
logo_enrichment:
enrichment_timestamp: '2025-12-23T17:05:32.209495+00:00'
source_url: http://www.city-yuzawa.jp/shisetsu0421/520.html
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: http://www.city-yuzawa.jp/apple-touch-icon.png
source_url: http://www.city-yuzawa.jp/shisetsu0421/520.html
css_selector: '[document] > html > head > link:nth-of-type(3)'
retrieved_on: '2025-12-23T17:05:32.209495+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
summary:
total_claims: 1
has_primary_logo: false
has_favicon: true
has_og_image: false
favicon_count: 2

View file

@ -32,18 +32,19 @@ ghcid:
generation_timestamp: '2025-12-06T23:38:31.066995+00:00'
location_resolution:
country_code: JP
region_code: 05
region_code: 5
city_code: YUZ
method: CH_ANNOTATOR_SOURCE
ghcid_history:
- ghcid: JP-05-YUZ-M-ISMM
valid_from: "2025-12-10T09:43:29Z"
valid_from: '2025-12-10T09:43:29Z'
valid_to: null
reason: "Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO 3166-2:JP"
reason: Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO
3166-2:JP
- ghcid: JP-AK-YUZ-M-ISMM
valid_from: null
valid_to: "2025-12-10T09:43:29Z"
reason: "Previous GHCID with incorrect region code"
valid_to: '2025-12-10T09:43:29Z'
reason: Previous GHCID with incorrect region code
- ghcid: JP-AK-YUZ-M-ISMM
ghcid_numeric: 4849865788719712149
valid_from: '2025-12-06T23:38:31.066995+00:00'
@ -101,8 +102,8 @@ ch_annotator:
annotation_metadata:
confidence_score: 0.98
verified: false
verification_date:
verified_by:
verification_date: null
verified_by: null
entity_claims:
- claim_type: full_name
claim_value: INNAI SILVER-MINE MUSEUM
@ -215,7 +216,7 @@ wikidata_enrichment:
location:
city: Yuzawa Shi
region: Akita Ken
region_code: 05
region_code: 5
country: JP
postal_code: 019-0111
street_address: KAMIINNAI, Yuzawa Shi, Akita Ken, 019-0111
@ -230,3 +231,22 @@ location:
geonames_id: 2110460
geonames_name: Yuzawa
feature_code: PPLA2
logo_enrichment:
enrichment_timestamp: '2025-12-23T17:05:37.960769+00:00'
source_url: https://www.city-yuzawa.jp/soshiki/90/2913.html
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: https://www.city-yuzawa.jp/apple-touch-icon.png
source_url: https://www.city-yuzawa.jp/soshiki/90/2913.html
css_selector: '[document] > html > head > link:nth-of-type(3)'
retrieved_on: '2025-12-23T17:05:37.960769+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
summary:
total_claims: 1
has_primary_logo: false
has_favicon: true
has_og_image: false
favicon_count: 2

View file

@ -546,3 +546,37 @@ youtube_enrichment:
comments: []
thumbnail_url: https://i.ytimg.com/vi/A3aHuXI0GEw/hqdefault.jpg
status: SUCCESS
logo_enrichment:
enrichment_timestamp: '2025-12-23T17:05:57.288773+00:00'
source_url: http://asakura-museum.pref.fukui.lg.jp
extraction_method: crawl4ai
claims:
- claim_type: logo_url
claim_value: https://asakura-museum.pref.fukui.lg.jp/theme/ver2022/img/common/logo/type1-white.png
source_url: http://asakura-museum.pref.fukui.lg.jp
css_selector: '#HeaderMenuArea > div.PageWidthSetter.Wide > div.SiteHeaderBlock
> div.BlockHeader.bottom > h1.SiteLogo > a > img'
retrieved_on: '2025-12-23T17:05:57.288773+00:00'
extraction_method: crawl4ai_header_logo
detection_confidence: high
alt_text: ''
- claim_type: favicon_url
claim_value: http://asakura-museum.pref.fukui.lg.jp/theme/ver2022/img/common/icon/sp_favicon.png?_=20220921
source_url: http://asakura-museum.pref.fukui.lg.jp
css_selector: '[document] > html.chrome.chrome134 > head > link:nth-of-type(8)'
retrieved_on: '2025-12-23T17:05:57.288773+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: 144x144
- claim_type: og_image_url
claim_value: https://asakura-museum.pref.fukui.lg.jp/theme/ver2022/img/common/ogp.png
source_url: http://asakura-museum.pref.fukui.lg.jp
css_selector: '[document] > html.chrome.chrome134 > head > meta:nth-of-type(12)'
retrieved_on: '2025-12-23T17:05:57.288773+00:00'
extraction_method: crawl4ai_meta_og
summary:
total_claims: 3
has_primary_logo: true
has_favicon: true
has_og_image: true
favicon_count: 2

View file

@ -358,3 +358,28 @@ location:
geonames_id: 9865215
feature_code: PPL
normalization_timestamp: '2025-12-09T06:53:27.239068+00:00'
logo_enrichment:
enrichment_timestamp: '2025-12-23T17:06:10.256942+00:00'
source_url: http://toshokan.city.fukuoka.lg.jp
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: http://toshokan.city.fukuoka.lg.jp/favicon.ico
source_url: http://toshokan.city.fukuoka.lg.jp
css_selector: '[document] > html > head > link'
retrieved_on: '2025-12-23T17:06:10.256942+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: image/x-icon
favicon_sizes: ''
- claim_type: og_image_url
claim_value: https://toshokan.city.fukuoka.lg.jp/img/og.jpg
source_url: http://toshokan.city.fukuoka.lg.jp
css_selector: '[document] > html > head > meta:nth-of-type(11)'
retrieved_on: '2025-12-23T17:06:10.256942+00:00'
extraction_method: crawl4ai_meta_og
summary:
total_claims: 2
has_primary_logo: false
has_favicon: true
has_og_image: true
favicon_count: 1

View file

@ -632,3 +632,22 @@ youtube_enrichment:
comments: []
thumbnail_url: https://i.ytimg.com/vi/up0K74Tz10Q/hqdefault.jpg
status: SUCCESS
logo_enrichment:
enrichment_timestamp: '2025-12-23T17:08:07.511730+00:00'
source_url: http://info.pref.fukui.jp/koreki/index.html
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: http://info.pref.fukui.jp/koreki/img/fukuiicon.png
source_url: http://info.pref.fukui.jp/koreki/index.html
css_selector: '[document] > html > head > link:nth-of-type(4)'
retrieved_on: '2025-12-23T17:08:07.511730+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
summary:
total_claims: 1
has_primary_logo: false
has_favicon: true
has_og_image: false
favicon_count: 1

View file

@ -443,3 +443,22 @@ location:
geonames_id: 9865219
feature_code: PPL
normalization_timestamp: '2025-12-09T06:53:27.456012+00:00'
logo_enrichment:
enrichment_timestamp: '2025-12-23T17:08:16.365626+00:00'
source_url: https://www.library-archives.pref.fukui.lg.jp
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: https://www.library-archives.pref.fukui.lg.jp/favicon.ico
source_url: https://www.library-archives.pref.fukui.lg.jp
css_selector: '[document] > html > head > link'
retrieved_on: '2025-12-23T17:08:16.365626+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
summary:
total_claims: 1
has_primary_logo: false
has_favicon: true
has_og_image: false
favicon_count: 1

View file

@ -101,3 +101,10 @@ provenance:
- CRITICAL - LinkedIn had WRONG website linked (museumstevensweert.nl instead of papierknipmuseum.nl)
- Address verified via correct museum website research on 2025-12-17
- Founded in 1950s by Wiecher Lever, moved to Westerbork in 1965
wikidata_enrichment:
wikidata_id: Q19832258
wikidata_url: https://www.wikidata.org/wiki/Q19832258
label: Museum van Papierknipkunst
description: Museum van Papierknipkunst
enrichment_timestamp: '2025-01-13T00:00:00Z'
enrichment_method: manual_wikidata_lookup

View file

@ -100,3 +100,10 @@ provenance:
- Province corrected from GR (Groningen) to DR (Drenthe)
- City resolved from XXX to ZUI (Zuidlaren)
- LinkedIn location field was incorrect - actual address is in Drenthe
wikidata_enrichment:
wikidata_id: null
label: Doe Museum
description: museum in Zuidlaren, Netherlands
enrichment_timestamp: '2025-01-13T00:00:00Z'
enrichment_method: manual_wikidata_lookup
notes: No Wikidata entry found for this institution

View file

@ -83,3 +83,10 @@ provenance:
- Created from unmatched LinkedIn company profile
- 'Location resolution method: UNRESOLVED'
- Location enriched from institution name on 2025-12-16
wikidata_enrichment:
wikidata_id: null
label: Dutch Digital Art Museum Almere (DDAMA)
description: museum in Almere, Netherlands
enrichment_timestamp: '2025-01-13T00:00:00Z'
enrichment_method: manual_wikidata_lookup
notes: No Wikidata entry found for this institution

View file

@ -74,3 +74,10 @@ provenance:
notes:
- Created from unmatched LinkedIn company profile
- 'Location resolution method: CITY_INFERRED_FROM_NAME'
wikidata_enrichment:
wikidata_id: null
label: Museum Nagele
description: museum in Nagele, Netherlands
enrichment_timestamp: '2025-01-13T00:00:00Z'
enrichment_method: manual_wikidata_lookup
notes: No Wikidata entry found for this institution

View file

@ -73,3 +73,10 @@ provenance:
notes:
- Created from unmatched LinkedIn company profile
- 'Location resolution method: CITY_INFERRED_FROM_NAME'
wikidata_enrichment:
wikidata_id: null
label: Museum De Waach Aldeboarn
description: museum in Aldeboarn, Netherlands
enrichment_timestamp: '2025-01-13T00:00:00Z'
enrichment_method: manual_wikidata_lookup
notes: No Wikidata entry found for this institution

View file

@ -74,3 +74,10 @@ provenance:
notes:
- Created from unmatched LinkedIn company profile
- 'Location resolution method: CITY_INFERRED_FROM_NAME'
wikidata_enrichment:
wikidata_id: null
label: Museum Boer Kip
description: museum in Boer, Netherlands
enrichment_timestamp: '2025-01-13T00:00:00Z'
enrichment_method: manual_wikidata_lookup
notes: No Wikidata entry found for this institution

View file

@ -81,3 +81,11 @@ provenance:
notes:
- Created from unmatched LinkedIn company profile
- 'Location resolution method: CITY_INFERRED_FROM_NAME'
wikidata_enrichment:
wikidata_id: null
label: Museum Buren en Oranje
description: museum in Buren (Friesland), Netherlands
enrichment_timestamp: '2025-01-13T00:00:00Z'
enrichment_method: manual_wikidata_lookup
notes: No Wikidata entry found for this institution. Note - Q98893871 is Museum Buren
en Oranje in Buren (Gelderland), which is a different institution.

View file

@ -870,3 +870,10 @@ logo_enrichment:
has_favicon: true
has_og_image: false
favicon_count: 1
wikidata_enrichment:
wikidata_id: null
label: Bibliotheken Noord Fryslân
description: library in Dokkum, Netherlands
enrichment_timestamp: '2025-01-13T00:00:00Z'
enrichment_method: manual_wikidata_lookup
notes: No Wikidata entry found for this institution

View file

@ -73,3 +73,11 @@ provenance:
notes:
- Created from unmatched LinkedIn company profile
- 'Location resolution method: CITY_INFERRED_FROM_NAME'
wikidata_enrichment:
wikidata_id: Q1863317
wikidata_url: https://www.wikidata.org/wiki/Q1863317
label: Museum Dokkum
description: museum in Friesland
enrichment_timestamp: '2025-01-13T00:00:00Z'
enrichment_method: manual_wikidata_lookup
notes: LinkedIn emic_name contains artifact "Naar beginpagina" (homepage link text) - actual name is Museum Dokkum

View file

@ -82,3 +82,10 @@ provenance:
- Created from unmatched LinkedIn company profile
- 'Location resolution method: UNRESOLVED'
- 'Location enriched on 2025-12-17 via Exa web search: Grou, Friesland'
wikidata_enrichment:
wikidata_id: Q20622462
wikidata_url: https://www.wikidata.org/wiki/Q20622462
label: Mineralogisch Museum
description: museum in Grou, Nederland
enrichment_timestamp: '2025-01-13T00:00:00Z'
enrichment_method: manual_wikidata_lookup

View file

@ -117,3 +117,11 @@ provenance:
notes:
- Enriched from institutional website with verified address
- Emic name corrected from English to Dutch
wikidata_enrichment:
wikidata_id: Q12012586
wikidata_url: https://www.wikidata.org/wiki/Q12012586
label: De Spitkeet
description: museum in Friesland
enrichment_timestamp: '2025-01-13T00:00:00Z'
enrichment_method: manual_wikidata_lookup
notes: Wikidata uses short name "De Spitkeet", full name is "Openluchtmuseum De Spitkeet"

View file

@ -110,3 +110,12 @@ provenance:
- Created from unmatched LinkedIn company profile
- Location verified via web research - De Dunen 3, 9281 KT Harkema
- Upgraded from NL-XX-XXX-M-OAMS to NL-FR-HAR-M-OMS
- POTENTIAL DUPLICATE - See also NL-FR-HAR-M-ODS.yaml (same museum)
wikidata_enrichment:
wikidata_id: Q12012586
wikidata_url: https://www.wikidata.org/wiki/Q12012586
label: De Spitkeet
description: museum in Friesland
enrichment_timestamp: '2025-01-13T00:00:00Z'
enrichment_method: manual_wikidata_lookup
notes: Wikidata uses short name "De Spitkeet", full name is "Openluchtmuseum De Spitkeet"

View file

@ -92,3 +92,10 @@ provenance:
notes:
- Created from unmatched LinkedIn company profile
- 'Location resolution method: GEONAMES_LOOKUP'
wikidata_enrichment:
wikidata_id: Q141355
wikidata_url: https://www.wikidata.org/wiki/Q141355
label: Museum Hindeloopen
description: museum in Súdwest-Fryslân
enrichment_timestamp: '2025-01-13T00:00:00Z'
enrichment_method: manual_wikidata_lookup

View file

@ -97,3 +97,10 @@ provenance:
- Address verified via official website on 2025-12-17
- 'Previous location resolution method: UNRESOLVED'
- 'Current location resolution method: VERIFIED_ADDRESS'
wikidata_enrichment:
wikidata_id: Q2447114
wikidata_url: https://www.wikidata.org/wiki/Q2447114
label: Kollumer Museum Mr. Andreae
description: Streekmuseum in Friesland
enrichment_timestamp: '2025-01-13T00:00:00Z'
enrichment_method: manual_wikidata_lookup

View file

@ -79,3 +79,11 @@ provenance:
- Created from unmatched LinkedIn company profile
- 'Location resolution method: UNRESOLVED'
- Location enriched from institution name on 2025-12-16
wikidata_enrichment:
wikidata_id: Q2869457
wikidata_url: https://www.wikidata.org/wiki/Q2869457
label: Frysk Letterkundich Museum en Dokumintaasjesintrum
description: voormalig museum in Leeuwarden
enrichment_timestamp: '2025-01-13T00:00:00Z'
enrichment_method: manual_wikidata_lookup
notes: Wikidata indicates this is a former museum ("voormalig museum")

View file

@ -77,3 +77,10 @@ provenance:
notes:
- Created from unmatched LinkedIn company profile
- 'Location resolution method: GEONAMES_LOOKUP'
wikidata_enrichment:
wikidata_id: null
label: The Living Museum Leeuwarden
description: museum in Leeuwarden, Netherlands
enrichment_timestamp: '2025-01-13T00:00:00Z'
enrichment_method: manual_wikidata_lookup
notes: No Wikidata entry found for this institution

View file

@ -114,3 +114,10 @@ provenance:
- Created from unmatched LinkedIn company profile
- Enriched with location and contact details from official website
- Location resolved via GeoNames to Leeuwarden, Friesland
wikidata_enrichment:
wikidata_id: null
label: Scouting Museum Fryslân
description: museum in Leeuwarden, Netherlands
enrichment_timestamp: '2025-01-13T00:00:00Z'
enrichment_method: manual_wikidata_lookup
notes: No Wikidata entry found for this institution

View file

@ -70,3 +70,10 @@ provenance:
notes:
- Created from unmatched LinkedIn company profile
- 'Location resolution method: CITY_INFERRED_FROM_NAME'
wikidata_enrichment:
wikidata_id: null
label: Museum Lemmer
description: museum in Lemmer, Netherlands
enrichment_timestamp: '2025-01-13T00:00:00Z'
enrichment_method: manual_wikidata_lookup
notes: No Wikidata entry found for this institution

View file

@ -76,3 +76,11 @@ identifiers:
- identifier_scheme: Wikidata
identifier_value: Q13137168
identifier_url: https://www.wikidata.org/wiki/Q13137168
wikidata_enrichment:
wikidata_id: Q13137168
wikidata_url: https://www.wikidata.org/wiki/Q13137168
label: Museum Sloten
description: museum in Sloten
enrichment_timestamp: '2025-01-13T00:00:00Z'
enrichment_method: manual_wikidata_lookup
notes: Museum Stedhûs Sleat is the Frisian name; also known as Museum Sloten

View file

@ -128,3 +128,10 @@ provenance:
- Private museum dedicated to Indian motorcycles
- Operated by Tony "Indian" Leenes
- LinkedIn follower count of 5.6M is anomalous data error
wikidata_enrichment:
wikidata_id: null
label: Tony Leenes Indian Motorcycle Museum
description: private motorcycle museum in Lemmer, Netherlands
enrichment_timestamp: '2025-01-13T00:00:00Z'
enrichment_method: manual_wikidata_lookup
notes: No Wikidata entry found for this institution

View file

@ -124,3 +124,11 @@ provenance:
- Created from unmatched LinkedIn company profile
- 'Original location resolution method: PROVINCE_FROM_CITY_FIELD'
- '2025-12-20: City resolved XXX→MOD, website corrected, KvK and parent organization added based on official website research'
wikidata_enrichment:
wikidata_id: Q7477577
wikidata_url: https://www.wikidata.org/wiki/Q7477577
label: Museum 't Fiskershúske
description: bouwwerk in Dongeradeel
enrichment_timestamp: '2025-01-13T00:00:00Z'
enrichment_method: manual_wikidata_lookup
notes: Open-air museum about traditional Wadden Sea fishing culture

View file

@ -73,3 +73,11 @@ provenance:
notes:
- Created from unmatched LinkedIn company profile
- 'Location resolution method: CITY_INFERRED_FROM_NAME'
wikidata_enrichment:
wikidata_id: Q2743903
wikidata_url: https://www.wikidata.org/wiki/Q2743903
label: Rien Poortvlietmuseum
description: museum over de beeldend kunstenaar Rien Poortvliet
enrichment_timestamp: '2025-01-13T00:00:00Z'
enrichment_method: manual_wikidata_lookup
notes: Museum dedicated to artist Rien Poortvliet; location in GHCID may be incorrect (Rien is a village, not where this museum is)

View file

@ -70,3 +70,10 @@ provenance:
notes:
- Created from unmatched LinkedIn company profile
- 'Location resolution method: CITY_INFERRED_FROM_NAME'
wikidata_enrichment:
wikidata_id: null
label: Stichting Rien Poortvliet Museum Korendijk
description: foundation for Rien Poortvliet museum
enrichment_timestamp: '2025-01-13T00:00:00Z'
enrichment_method: manual_wikidata_lookup
notes: No separate Wikidata entry for the foundation; may be related to Q2743903 (Rien Poortvlietmuseum)

View file

@ -105,3 +105,10 @@ provenance:
- Location resolved from institutional website showing address in Ryptsjerk
- Private museum run by Siem Terpstra, visits by appointment only
- Not affiliated with official STIHL Brand World in Germany
wikidata_enrichment:
wikidata_id: null
label: Stihl Museum
description: private chainsaw museum in Ryptsjerk, Netherlands
enrichment_timestamp: '2025-01-13T00:00:00Z'
enrichment_method: manual_wikidata_lookup
notes: No Wikidata entry found for this private museum

View file

@ -76,3 +76,10 @@ provenance:
- Created from unmatched LinkedIn company profile
- 'Location resolution method: UNRESOLVED'
- Location enriched from institution name on 2025-12-16
wikidata_enrichment:
wikidata_id: Q79317785
wikidata_url: https://www.wikidata.org/wiki/Q79317785
label: Bunker Museum Terschelling
description: museum op Terschelling
enrichment_timestamp: '2025-01-13T00:00:00Z'
enrichment_method: manual_wikidata_lookup

View file

@ -70,3 +70,10 @@ provenance:
notes:
- Created from unmatched LinkedIn company profile
- 'Location resolution method: CITY_INFERRED_FROM_NAME'
wikidata_enrichment:
wikidata_id: null
label: Museum Warten
description: museum in Warten, Netherlands
enrichment_timestamp: '2025-01-13T00:00:00Z'
enrichment_method: manual_wikidata_lookup
notes: No Wikidata entry found for this institution

View file

@ -536,8 +536,13 @@ ch_annotator:
integrated_from: netherlands_complete_ch_annotator.yaml
integration_date: '2025-12-06T23:20:45.782206+00:00'
match_type: name
wikidata_enrichment_status: NOT_FOUND
wikidata_search_timestamp: '2025-12-08T08:52:13.003305+00:00'
wikidata_enrichment:
wikidata_id: null
label: Bibliotheek Wolvega
description: library in Wolvega, Netherlands
enrichment_timestamp: '2025-01-13T00:00:00Z'
enrichment_method: manual_wikidata_lookup
notes: No Wikidata entry found for this institution. Previous search 2025-12-08 also not found.
location:
latitude: 52.8771493
longitude: 6.0055689

View file

@ -82,3 +82,10 @@ provenance:
- Created from unmatched LinkedIn company profile
- 'Location resolution method: UNRESOLVED'
- 'Location enriched on 2025-12-17 via Exa web search: Workum, Friesland'
wikidata_enrichment:
wikidata_id: Q2786191
wikidata_url: https://www.wikidata.org/wiki/Q2786191
label: Jopie Huisman Museum
description: museum in Súdwest-Fryslân
enrichment_timestamp: '2025-01-13T00:00:00Z'
enrichment_method: manual_wikidata_lookup

View file

@ -114,3 +114,10 @@ provenance:
- Location resolved via GeoNames to Aalten, Gelderland
- LinkedIn website shortlink (lnkd.in/ezz5r9nF) is broken
- Museum may be for sale per saabmuseumforsale.nl
wikidata_enrichment:
wikidata_id: null
label: Saab Museum Kempink
description: private automobile museum in Aalten, Netherlands
enrichment_timestamp: '2025-01-13T00:00:00Z'
enrichment_method: manual_wikidata_lookup
notes: No Wikidata entry found for this institution

View file

@ -241,3 +241,10 @@ provenance:
notes:
- Created from unmatched LinkedIn company profile
- 'Location resolution method: GEONAMES_LOOKUP'
wikidata_enrichment:
wikidata_id: Q26258118
wikidata_url: https://www.wikidata.org/wiki/Q26258118
label: Kadaster
description: zelfstandig bestuursorgaan in Nederland
enrichment_timestamp: '2025-01-13T00:00:00Z'
enrichment_method: manual_wikidata_lookup

View file

@ -213,6 +213,14 @@ provenance:
notes:
- Created from unmatched LinkedIn company profile
- 'Location resolution method: PROVINCE_FROM_CITY_FIELD'
wikidata_enrichment:
wikidata_id: Q618187
wikidata_url: https://www.wikidata.org/wiki/Q618187
label: Apenheul
description: dierentuin in Nederland
enrichment_timestamp: '2025-01-13T00:00:00Z'
enrichment_method: manual_wikidata_lookup
notes: Wikidata ID already present in identifiers section
identifiers:
- identifier_scheme: Wikidata
identifier_value: Q618187

View file

@ -145,3 +145,10 @@ provenance:
- Created from unmatched LinkedIn company profile
- 'Original location resolution method: PROVINCE_FROM_CITY_FIELD'
- '2025-12-20: Province corrected FL→GE, city resolved XXX→APE. Distributed museum with visitor locations documented separately.'
wikidata_enrichment:
wikidata_id: null
label: Museum Bescherming Bevolking
description: civil protection museum in Apeldoorn, Netherlands
enrichment_timestamp: '2025-01-13T00:00:00Z'
enrichment_method: manual_wikidata_lookup
notes: No Wikidata entry found for this institution

View file

@ -97,3 +97,10 @@ provenance:
- Location verified via web search - museum website confirms Schotweg 63, 7312 AB Apeldoorn
- Small private museum, open by appointment only
- Founded 2001 by Jan Bark
wikidata_enrichment:
wikidata_id: null
label: Museum in de Zevende Hemel
description: private museum in Apeldoorn, Netherlands
enrichment_timestamp: '2025-01-13T00:00:00Z'
enrichment_method: manual_wikidata_lookup
notes: No Wikidata entry found for this institution

View file

@ -192,3 +192,10 @@ timespan:
sources:
- 'Linkup web search: https://www.yumpu.com/nl/document/view/31673067/stichting-indisch-thee-indisch-thee-familie-archief'
notes: 'Found via pattern: full_date_nl'
wikidata_enrichment:
wikidata_id: null
label: Stichting Indisch Familie Archief
description: archive in Arnhem, Netherlands
enrichment_timestamp: '2025-01-13T00:00:00Z'
enrichment_method: manual_wikidata_lookup
notes: No Wikidata entry found for this institution

View file

@ -315,3 +315,10 @@ logo_enrichment:
has_favicon: true
has_og_image: true
favicon_count: 3
wikidata_enrichment:
wikidata_id: null
label: Gemeente Texel
description: intangible heritage custodian in Den Burg, Netherlands
enrichment_timestamp: '2025-01-13T00:00:00Z'
enrichment_method: manual_wikidata_lookup
notes: Q9966 (Texel island/municipality) not used - describes geographic entity, not the heritage custodian function

View file

@ -255,3 +255,10 @@ timespan:
sources:
- 'Linkup web search: https://www.immaterieelerfgoed.nl/nl/kenniscentrum'
notes: 'Found via pattern: sinds'
wikidata_enrichment:
wikidata_id: null
label: Kenniscentrum Immaterieel Erfgoed Nederland
description: intangible heritage knowledge center in Arnhem, Netherlands
enrichment_timestamp: '2025-01-13T00:00:00Z'
enrichment_method: manual_wikidata_lookup
notes: No Wikidata entry found for this institution

View file

@ -380,3 +380,10 @@ logo_enrichment:
has_favicon: true
has_og_image: false
favicon_count: 1
wikidata_enrichment:
wikidata_id: null
label: De Stoelenmatter
description: intangible heritage custodian (chair caning) in Zundert, Netherlands
enrichment_timestamp: '2025-01-13T00:00:00Z'
enrichment_method: manual_wikidata_lookup
notes: No Wikidata entry found for this institution

Some files were not shown because too many files have changed in this diff Show more