- Add inferred birth dates using EDTF notation - Add inferred birth/current settlements - Enrich employment history with temporal data - Add heritage sector relevance scores - Improve PPID component tracking - Update .gitignore with large file patterns (warc, nt, trix, geonames.db)
464 lines
No EOL
29 KiB
JSON
464 lines
No EOL
29 KiB
JSON
{
|
|
"ppid": "ID_NL-GE-EDE_197X_NL-NH-AMS_XXXX_ANNABELLE-ARNTZ",
|
|
"ppid_type": "ID",
|
|
"ppid_components": {
|
|
"type": "ID",
|
|
"first_location": "NL-GE-EDE",
|
|
"first_date": "197X",
|
|
"last_location": "NL-NH-AMS",
|
|
"last_date": "XXXX",
|
|
"name_tokens": [
|
|
"ANNABELLE",
|
|
"ARNTZ"
|
|
],
|
|
"first_date_source": "inferred_birth_decade",
|
|
"last_location_source": "inferred_current_settlement",
|
|
"first_date_alternatives": [
|
|
"197X"
|
|
],
|
|
"first_location_source": "inferred_birth_settlement"
|
|
},
|
|
"name": "Annabelle Arntz",
|
|
"birth_date": {
|
|
"edtf": "XXXX",
|
|
"precision": "unknown",
|
|
"note": "See inferred_birth_decade for heuristic estimate"
|
|
},
|
|
"is_living": true,
|
|
"heritage_relevance": {
|
|
"is_heritage_relevant": true,
|
|
"heritage_types": [
|
|
"A"
|
|
],
|
|
"score": 0.82,
|
|
"score_rationale": "Hoofd Publiek at Noord-Hollands Archief since January 2024. Previously Hoofd Communicatie (2020-2024) and Senior Adviseur Communicatie en Marketing (2017-2020) at NHA - total 7+ years at the archive. Background in cultural communication: 8+ years at Duitsland Instituut Amsterdam (DIA), intern at Nederlands Letterenfonds. Education in German studies (Westfälische Wilhelms-Universität Münster, Universiteit van Amsterdam). 23+ years total experience. Score of 0.82 reflects: MT-level position at major archive (+0.25), long tenure at heritage institution (+0.20), communications expertise relevant to public engagement (+0.15), cultural sector background (+0.12), but not a trained archivist and primarily administrative/communications role rather than collections work (+0.10).",
|
|
"rationale": "Identified as staff at Noord-Hollands Archief"
|
|
},
|
|
"affiliations": [
|
|
{
|
|
"custodian_name": "Noord-Hollands Archief",
|
|
"custodian_slug": "noord-hollands-archief",
|
|
"role_title": "hoofd publiek Noord-Hollands Archief",
|
|
"heritage_relevant": true,
|
|
"heritage_type": "A",
|
|
"current": true,
|
|
"observed_on": "2025-12-14T11:22:06Z",
|
|
"source_url": "https://www.linkedin.com/company/noord-hollands-archief/people/"
|
|
}
|
|
],
|
|
"profile_data": {
|
|
"name": "Annabelle Arntz",
|
|
"linkedin_url": "https://www.linkedin.com/in/annabelle-arntz-18903057",
|
|
"headline": "hoofd publiek Noord-Hollands Archief",
|
|
"location": "Amsterdam, North Holland, Netherlands (NL)",
|
|
"connections": "500 connections • 706 followers",
|
|
"about": "Total Experience: 23 years and 4 months",
|
|
"experience": [
|
|
{
|
|
"title": "Hoofd Publiek",
|
|
"company": "Noord-Hollands Archief",
|
|
"date_range": "Jan 2024 - Present • 1 year and 10 months",
|
|
"location": "Haarlem"
|
|
},
|
|
{
|
|
"title": "Hoofd Communicatie",
|
|
"company": "Noord-Hollands Archief",
|
|
"date_range": "May 2020 - Apr 2024 • 3 years and 11 months",
|
|
"location": "Haarlem"
|
|
},
|
|
{
|
|
"title": "Senior Adviseur Communicatie En Marketing",
|
|
"company": "Noord-Hollands Archief",
|
|
"date_range": "Apr 2017 - May 2020 • 3 years and 1 month",
|
|
"location": "Haarlem en omgeving, Nederland"
|
|
},
|
|
{
|
|
"title": "Hoofd Pers En Communicatie, Conferenties En Evenementen",
|
|
"company": "Duitsland Instituut Amsterdam (DIA)",
|
|
"date_range": "Nov 2009 - Apr 2017 • 7 years and 5 months",
|
|
"location": "Amsterdam",
|
|
"description": "Aanspreekpunt voor de pers en partnerinstituten, budgetbeheer van de afdeling, verantwoordelijk voor het communicatiebeleid, social media en het niet-wetenschappelijke activiteitenprogramma in samenspraak met het management (planning en organisatie van conferenties, lezingen, seminars), huisstijl en een gedeelte van de website van het instituut."
|
|
},
|
|
{
|
|
"title": "Projectmanager Voorlichting En Projecten",
|
|
"company": "Duitsland Instituut Amsterdam (DIA)",
|
|
"date_range": "May 2008 - Nov 2009 • 1 year and 6 months",
|
|
"location": "Amsterdam"
|
|
},
|
|
{
|
|
"title": "Medewerker Voorlichting En Projecten",
|
|
"company": "Duitsland Instituut Amsterdam (DIA)",
|
|
"date_range": "Jan 2006 - Apr 2008 • 2 years and 3 months",
|
|
"location": "Amsterdam"
|
|
},
|
|
{
|
|
"title": "Stagiaire Afdeling Kinder- En Jeugdboeken",
|
|
"company": "Nederlands Literair Productie- en Vertalingenfonds (NLPVF) huidig Nederlands Letterenfonds",
|
|
"date_range": "Jul 2005 - Dec 2005 • 5 months",
|
|
"location": "Amsterdam"
|
|
},
|
|
{
|
|
"title": "Student-assistente Zentrum Für Niederlande-Studien",
|
|
"company": "Westfälische Wilhelms-Universität",
|
|
"date_range": "Jul 2003 - Aug 2005 • 2 years and 1 month",
|
|
"description": "Münster"
|
|
}
|
|
],
|
|
"education": [
|
|
{
|
|
"degree": "Drs./Diplom Regionalwissenschaftler, Nederland-Duitsland Studies",
|
|
"institution": "Westfälische Wilhelms-Universität Münster",
|
|
"date_range": "2000 - 2005 • 5 years"
|
|
},
|
|
{
|
|
"degree": "Master of Arts (M.A.), Magister Nederlands, Duits, Niederlande-Studien",
|
|
"institution": "Westfälische Wilhelms-Universität Münster",
|
|
"date_range": "1998 - 2005 • 7 years"
|
|
}
|
|
],
|
|
"skills": [
|
|
"marketing",
|
|
"r"
|
|
],
|
|
"languages": [],
|
|
"profile_image_url": "https://media.licdn.com/dms/image/v2/C5603AQHx_5spv_w5Rg/profile-displayphoto-shrink_200_200/profile-displayphoto-shrink_200_200/0/1605272109216?e=2147483647&v=beta&t=r40WY1PHpxZYN4cZ2u8nwmZw-px_IkNUagXromkYt08"
|
|
},
|
|
"web_claims": [
|
|
{
|
|
"claim_type": "full_name",
|
|
"claim_value": "Annabelle Arntz",
|
|
"source_url": "https://www.linkedin.com/in/annabelle-arntz-18903057",
|
|
"retrieved_on": "2025-12-14T11:22:06Z",
|
|
"retrieval_agent": "linkedin_html_parser",
|
|
"content_hash": {
|
|
"algorithm": "sha256",
|
|
"value": "sha256-PE9GVJvYrmQH9Veaap/IgtwpBNhnQjaFNcjdQEzi/Ws=",
|
|
"scope": "extracted_text"
|
|
},
|
|
"text_fragment": "#:~:text=Annabelle%20Arntz",
|
|
"w3c_selectors": [
|
|
{
|
|
"type": "TextQuoteSelector",
|
|
"exact": "Annabelle Arntz",
|
|
"prefix": "",
|
|
"suffix": ""
|
|
}
|
|
],
|
|
"prov": {
|
|
"wasDerivedFrom": "https://www.linkedin.com/in/annabelle-arntz-18903057"
|
|
},
|
|
"verification": {
|
|
"status": "verified",
|
|
"last_verified": "2025-12-28T18:35:24.378659+00:00"
|
|
},
|
|
"archive": {
|
|
"memento_uri": null,
|
|
"archive_source": "web.archive.org",
|
|
"note": "No Wayback Machine snapshot available as of query date",
|
|
"query_date": "2025-12-28T18:35:30.875879+00:00"
|
|
},
|
|
"glm_validation": {
|
|
"is_valid": false,
|
|
"semantic_category": "identity",
|
|
"validation_notes": "Source is a LinkedIn profile page (Social Media), not a Dutch heritage institution website. TextQuoteSelector cannot be generated as the 'extracted_text' field was empty. Identity claims on social media pages are generally dynamic, user-generated content rather than static institutional heritage data.",
|
|
"model": "glm-4.7",
|
|
"validated_at": "2025-12-28T18:51:50.850338+00:00"
|
|
}
|
|
},
|
|
{
|
|
"claim_type": "role_title",
|
|
"claim_value": "hoofd publiek Noord-Hollands Archief",
|
|
"source_url": "https://www.linkedin.com/in/annabelle-arntz-18903057",
|
|
"retrieved_on": "2025-12-14T11:22:06Z",
|
|
"retrieval_agent": "linkedin_html_parser",
|
|
"content_hash": {
|
|
"algorithm": "sha256",
|
|
"value": "sha256-FugO4NK01ILqXIv/soaep3fygBDMRb4hmWbXUDWdNI4=",
|
|
"scope": "extracted_text"
|
|
},
|
|
"text_fragment": "#:~:text=hoofd%20publiek%20Noord-Hollands%20Archief",
|
|
"w3c_selectors": [
|
|
{
|
|
"type": "TextQuoteSelector",
|
|
"exact": "hoofd publiek Noord-Hollands Archief",
|
|
"prefix": "",
|
|
"suffix": ""
|
|
}
|
|
],
|
|
"prov": {
|
|
"wasDerivedFrom": "https://www.linkedin.com/in/annabelle-arntz-18903057"
|
|
},
|
|
"verification": {
|
|
"status": "verified",
|
|
"last_verified": "2025-12-28T18:35:30.876253+00:00"
|
|
},
|
|
"archive": {
|
|
"memento_uri": null,
|
|
"archive_source": "web.archive.org",
|
|
"note": "No Wayback Machine snapshot available as of query date",
|
|
"query_date": "2025-12-28T18:35:32.035204+00:00"
|
|
},
|
|
"glm_validation": {
|
|
"is_valid": false,
|
|
"semantic_category": "role",
|
|
"validation_notes": "Claim extracted from a LinkedIn profile page, not the target institution's domain. CSS selector is 'none' and extracted_text is empty. Cannot generate TextQuoteSelectors (prefix/suffix) without the source text context. While the value represents a role, the data integrity is compromised by the lack of context and source verification.",
|
|
"model": "glm-4.7",
|
|
"validated_at": "2025-12-28T18:51:54.349649+00:00"
|
|
}
|
|
},
|
|
{
|
|
"claim_type": "full_name",
|
|
"claim_value": "Annabelle Arntz",
|
|
"source_url": "https://www.linkedin.com/in/annabelle-arntz-18903057",
|
|
"retrieved_on": "2025-12-14T11:22:06Z",
|
|
"retrieval_agent": "linkedin_html_parser",
|
|
"content_hash": {
|
|
"algorithm": "sha256",
|
|
"value": "sha256-PE9GVJvYrmQH9Veaap/IgtwpBNhnQjaFNcjdQEzi/Ws=",
|
|
"scope": "extracted_text"
|
|
},
|
|
"text_fragment": "#:~:text=Annabelle%20Arntz",
|
|
"w3c_selectors": [
|
|
{
|
|
"type": "TextQuoteSelector",
|
|
"exact": "Annabelle Arntz",
|
|
"prefix": "",
|
|
"suffix": ""
|
|
}
|
|
],
|
|
"prov": {
|
|
"wasDerivedFrom": "https://www.linkedin.com/in/annabelle-arntz-18903057"
|
|
},
|
|
"verification": {
|
|
"status": "verified",
|
|
"last_verified": "2025-12-28T18:35:24.378659+00:00"
|
|
},
|
|
"archive": {
|
|
"memento_uri": null,
|
|
"archive_source": "web.archive.org",
|
|
"note": "No Wayback Machine snapshot available as of query date",
|
|
"query_date": "2025-12-28T18:35:30.875879+00:00"
|
|
},
|
|
"glm_validation": {
|
|
"is_valid": false,
|
|
"semantic_category": "identity",
|
|
"validation_notes": "Source is a LinkedIn profile page (Social Media), not a Dutch heritage institution website. TextQuoteSelector cannot be generated as the 'extracted_text' field was empty. Identity claims on social media pages are generally dynamic, user-generated content rather than static institutional heritage data.",
|
|
"model": "glm-4.7",
|
|
"validated_at": "2025-12-28T18:51:50.850338+00:00"
|
|
}
|
|
},
|
|
{
|
|
"claim_type": "role_title",
|
|
"claim_value": "hoofd publiek Noord-Hollands Archief",
|
|
"source_url": "https://www.linkedin.com/in/annabelle-arntz-18903057",
|
|
"retrieved_on": "2025-12-14T11:22:06Z",
|
|
"retrieval_agent": "linkedin_html_parser",
|
|
"content_hash": {
|
|
"algorithm": "sha256",
|
|
"value": "sha256-FugO4NK01ILqXIv/soaep3fygBDMRb4hmWbXUDWdNI4=",
|
|
"scope": "extracted_text"
|
|
},
|
|
"text_fragment": "#:~:text=hoofd%20publiek%20Noord-Hollands%20Archief",
|
|
"w3c_selectors": [
|
|
{
|
|
"type": "TextQuoteSelector",
|
|
"exact": "hoofd publiek Noord-Hollands Archief",
|
|
"prefix": "",
|
|
"suffix": ""
|
|
}
|
|
],
|
|
"prov": {
|
|
"wasDerivedFrom": "https://www.linkedin.com/in/annabelle-arntz-18903057"
|
|
},
|
|
"verification": {
|
|
"status": "verified",
|
|
"last_verified": "2025-12-28T18:35:30.876253+00:00"
|
|
},
|
|
"archive": {
|
|
"memento_uri": null,
|
|
"archive_source": "web.archive.org",
|
|
"note": "No Wayback Machine snapshot available as of query date",
|
|
"query_date": "2025-12-28T18:35:32.035204+00:00"
|
|
},
|
|
"glm_validation": {
|
|
"is_valid": false,
|
|
"semantic_category": "role",
|
|
"validation_notes": "Claim extracted from a LinkedIn profile page, not the target institution's domain. CSS selector is 'none' and extracted_text is empty. Cannot generate TextQuoteSelectors (prefix/suffix) without the source text context. While the value represents a role, the data integrity is compromised by the lack of context and source verification.",
|
|
"model": "glm-4.7",
|
|
"validated_at": "2025-12-28T18:51:54.349649+00:00"
|
|
}
|
|
},
|
|
{
|
|
"claim_type": "linkedin_url",
|
|
"claim_value": "https://www.linkedin.com/in/annabelle-arntz-18903057",
|
|
"source_url": "https://www.linkedin.com/company/noord-hollands-archief/people/",
|
|
"retrieved_on": "2025-12-12T21:58:47.350000+00:00",
|
|
"statement_created_at": "2026-01-09T22:45:50.810260+00:00",
|
|
"source_archived_at": "2025-12-12T21:58:47.350000+00:00",
|
|
"xpath": "/html[1]/head[1]/meta[1]/meta[2]/meta[3]/meta[4]/meta[5]/meta[6]/meta[7]/meta[8]/meta[9]/meta[10]/meta[11]/meta[12]/meta[13]/meta[14]/link[1]/link[2]/link[3]/link[4]/link[5]/link[6]/link[7]/meta[15]/meta[16]/meta[17]/meta[18]/meta[19]/meta[20]/meta[21]/meta[22]/meta[23]/meta[24]/meta[25]/meta[26]/link[8]/link[9]/link[10]/link[11]/link[12]/meta[27]/meta[28]/meta[29]/meta[30]/meta[31]/meta[32]/meta[33]/meta[34]/meta[35]/meta[36]/meta[37]/meta[38]/meta[39]/meta[40]/meta[41]/meta[42]/meta[43]/meta[44]/meta[45]/meta[46]/meta[47]/meta[48]/meta[49]/meta[50]/meta[51]/meta[52]/meta[53]/meta[54]/meta[55]/meta[56]/meta[57]/meta[58]/meta[59]/meta[60]/meta[61]/meta[62]/meta[63]/meta[64]/meta[65]/meta[66]/meta[67]/meta[68]/meta[69]/meta[70]/meta[71]/meta[72]/meta[73]/meta[74]/meta[75]/meta[76]/meta[77]/meta[78]/meta[79]/meta[80]/meta[81]/meta[82]/meta[83]/meta[84]/meta[85]/meta[86]/meta[87]/meta[88]/meta[89]/meta[90]/meta[91]/meta[92]/meta[93]/meta[94]/meta[95]/meta[96]/meta[97]/meta[98]/meta[99]/meta[100]/meta[101]/meta[102]/meta[103]/meta[104]/meta[105]/meta[106]/meta[107]/meta[108]/meta[109]/meta[110]/meta[111]/meta[112]/meta[113]/meta[114]/meta[115]/meta[116]/meta[117]/meta[118]/meta[119]/meta[120]/meta[121]/meta[122]/meta[123]/meta[124]/meta[125]/meta[126]/meta[127]/meta[128]/meta[129]/meta[130]/meta[131]/meta[132]/meta[133]/meta[134]/meta[135]/meta[136]/meta[137]/meta[138]/meta[139]/meta[140]/meta[141]/link[13]/link[14]/meta[142]/meta[143]/link[15]/link[16]/link[17]/link[18]/link[19]/link[20]/link[21]/link[22]/link[23]/link[24]/link[25]/link[26]/link[27]/link[28]/link[29]/link[30]/link[31]/link[32]/link[33]/link[34]/link[35]/link[36]/link[37]/link[38]/link[39]/link[40]/link[41]/body[1]/img[1]/img[2]/img[3]/img[4]/img[5]/img[6]/img[7]/img[8]/img[9]/img[10]/img[11]/img[12]/img[13]/img[14]/img[15]/img[16]/img[17]/div[28]/header[2]/div[32]/div[63]/div[64]/div[66]/div[67]/div[71]/main[1]/div[72]/section[2]/div[108]/div[109]/div[110]/div[158]/div[159]/div[160]/ul[5]/li[27]/div[161]/li[28]/div[173]/li[29]/div[185]/li[30]/div[197]/li[31]/div[209]/li[32]/div[221]/li[33]/div[233]/li[34]/div[245]/li[35]/div[257]/li[36]/div[269]/li[37]/div[281]/li[38]/div[293]/li[39]/div[305]/li[40]/div[317]/li[41]/div[329]/li[42]/div[341]/li[43]/div[353]/li[44]/div[365]/li[45]/div[377]/li[46]/div[389]/li[47]/div[401]/li[48]/div[415]/li[49]/div[427]/li[50]/div[439]/li[51]/div[451]/li[52]/div[463]/li[53]/div[475]/li[54]/div[487]/li[55]/div[499]/section[32]/img[77]/div[500]/div[501]/div[502]/a[73]",
|
|
"html_file": "/Volumes/KINGSTON/data/glam/data/custodian/person/affiliated/manual/(7) Noord-Hollands Archief_ People _ LinkedIn.html",
|
|
"xpath_match_score": 1.0,
|
|
"retrieval_agent": "extract_persons_with_provenance.py"
|
|
},
|
|
{
|
|
"claim_type": "full_name",
|
|
"claim_value": "Annabelle Arntz",
|
|
"source_url": "https://www.linkedin.com/company/noord-hollands-archief/people/",
|
|
"retrieved_on": "2025-12-12T21:58:47.350000+00:00",
|
|
"statement_created_at": "2026-01-09T22:45:50.810282+00:00",
|
|
"source_archived_at": "2025-12-12T21:58:47.350000+00:00",
|
|
"xpath": "/html[1]/head[1]/meta[1]/meta[2]/meta[3]/meta[4]/meta[5]/meta[6]/meta[7]/meta[8]/meta[9]/meta[10]/meta[11]/meta[12]/meta[13]/meta[14]/link[1]/link[2]/link[3]/link[4]/link[5]/link[6]/link[7]/meta[15]/meta[16]/meta[17]/meta[18]/meta[19]/meta[20]/meta[21]/meta[22]/meta[23]/meta[24]/meta[25]/meta[26]/link[8]/link[9]/link[10]/link[11]/link[12]/meta[27]/meta[28]/meta[29]/meta[30]/meta[31]/meta[32]/meta[33]/meta[34]/meta[35]/meta[36]/meta[37]/meta[38]/meta[39]/meta[40]/meta[41]/meta[42]/meta[43]/meta[44]/meta[45]/meta[46]/meta[47]/meta[48]/meta[49]/meta[50]/meta[51]/meta[52]/meta[53]/meta[54]/meta[55]/meta[56]/meta[57]/meta[58]/meta[59]/meta[60]/meta[61]/meta[62]/meta[63]/meta[64]/meta[65]/meta[66]/meta[67]/meta[68]/meta[69]/meta[70]/meta[71]/meta[72]/meta[73]/meta[74]/meta[75]/meta[76]/meta[77]/meta[78]/meta[79]/meta[80]/meta[81]/meta[82]/meta[83]/meta[84]/meta[85]/meta[86]/meta[87]/meta[88]/meta[89]/meta[90]/meta[91]/meta[92]/meta[93]/meta[94]/meta[95]/meta[96]/meta[97]/meta[98]/meta[99]/meta[100]/meta[101]/meta[102]/meta[103]/meta[104]/meta[105]/meta[106]/meta[107]/meta[108]/meta[109]/meta[110]/meta[111]/meta[112]/meta[113]/meta[114]/meta[115]/meta[116]/meta[117]/meta[118]/meta[119]/meta[120]/meta[121]/meta[122]/meta[123]/meta[124]/meta[125]/meta[126]/meta[127]/meta[128]/meta[129]/meta[130]/meta[131]/meta[132]/meta[133]/meta[134]/meta[135]/meta[136]/meta[137]/meta[138]/meta[139]/meta[140]/meta[141]/link[13]/link[14]/meta[142]/meta[143]/link[15]/link[16]/link[17]/link[18]/link[19]/link[20]/link[21]/link[22]/link[23]/link[24]/link[25]/link[26]/link[27]/link[28]/link[29]/link[30]/link[31]/link[32]/link[33]/link[34]/link[35]/link[36]/link[37]/link[38]/link[39]/link[40]/link[41]/body[1]/img[1]/img[2]/img[3]/img[4]/img[5]/img[6]/img[7]/img[8]/img[9]/img[10]/img[11]/img[12]/img[13]/img[14]/img[15]/img[16]/img[17]/div[28]/header[2]/div[32]/div[63]/div[64]/div[66]/div[67]/div[71]/main[1]/div[72]/section[2]/div[108]/div[109]/div[110]/div[158]/div[159]/div[160]/ul[5]/li[27]/div[161]/li[28]/div[173]/li[29]/div[185]/li[30]/div[197]/li[31]/div[209]/li[32]/div[221]/li[33]/div[233]/li[34]/div[245]/li[35]/div[257]/li[36]/div[269]/li[37]/div[281]/li[38]/div[293]/li[39]/div[305]/li[40]/div[317]/li[41]/div[329]/li[42]/div[341]/li[43]/div[353]/li[44]/div[365]/li[45]/div[377]/li[46]/div[389]/li[47]/div[401]/li[48]/div[415]/li[49]/div[427]/li[50]/div[439]/li[51]/div[451]/li[52]/div[463]/li[53]/div[475]/li[54]/div[487]/li[55]/div[499]/section[32]/img[77]/div[500]/div[501]/div[502]/a[73]/img[78]/@alt",
|
|
"html_file": "/Volumes/KINGSTON/data/glam/data/custodian/person/affiliated/manual/(7) Noord-Hollands Archief_ People _ LinkedIn.html",
|
|
"xpath_match_score": 1.0,
|
|
"retrieval_agent": "extract_persons_with_provenance.py"
|
|
},
|
|
{
|
|
"claim_type": "connection_degree",
|
|
"claim_value": "2nd",
|
|
"source_url": "https://www.linkedin.com/company/noord-hollands-archief/people/",
|
|
"retrieved_on": "2025-12-12T21:58:47.350000+00:00",
|
|
"statement_created_at": "2026-01-09T22:45:50.810349+00:00",
|
|
"source_archived_at": "2025-12-12T21:58:47.350000+00:00",
|
|
"xpath": "/html[1]/head[1]/meta[1]/meta[2]/meta[3]/meta[4]/meta[5]/meta[6]/meta[7]/meta[8]/meta[9]/meta[10]/meta[11]/meta[12]/meta[13]/meta[14]/link[1]/link[2]/link[3]/link[4]/link[5]/link[6]/link[7]/meta[15]/meta[16]/meta[17]/meta[18]/meta[19]/meta[20]/meta[21]/meta[22]/meta[23]/meta[24]/meta[25]/meta[26]/link[8]/link[9]/link[10]/link[11]/link[12]/meta[27]/meta[28]/meta[29]/meta[30]/meta[31]/meta[32]/meta[33]/meta[34]/meta[35]/meta[36]/meta[37]/meta[38]/meta[39]/meta[40]/meta[41]/meta[42]/meta[43]/meta[44]/meta[45]/meta[46]/meta[47]/meta[48]/meta[49]/meta[50]/meta[51]/meta[52]/meta[53]/meta[54]/meta[55]/meta[56]/meta[57]/meta[58]/meta[59]/meta[60]/meta[61]/meta[62]/meta[63]/meta[64]/meta[65]/meta[66]/meta[67]/meta[68]/meta[69]/meta[70]/meta[71]/meta[72]/meta[73]/meta[74]/meta[75]/meta[76]/meta[77]/meta[78]/meta[79]/meta[80]/meta[81]/meta[82]/meta[83]/meta[84]/meta[85]/meta[86]/meta[87]/meta[88]/meta[89]/meta[90]/meta[91]/meta[92]/meta[93]/meta[94]/meta[95]/meta[96]/meta[97]/meta[98]/meta[99]/meta[100]/meta[101]/meta[102]/meta[103]/meta[104]/meta[105]/meta[106]/meta[107]/meta[108]/meta[109]/meta[110]/meta[111]/meta[112]/meta[113]/meta[114]/meta[115]/meta[116]/meta[117]/meta[118]/meta[119]/meta[120]/meta[121]/meta[122]/meta[123]/meta[124]/meta[125]/meta[126]/meta[127]/meta[128]/meta[129]/meta[130]/meta[131]/meta[132]/meta[133]/meta[134]/meta[135]/meta[136]/meta[137]/meta[138]/meta[139]/meta[140]/meta[141]/link[13]/link[14]/meta[142]/meta[143]/link[15]/link[16]/link[17]/link[18]/link[19]/link[20]/link[21]/link[22]/link[23]/link[24]/link[25]/link[26]/link[27]/link[28]/link[29]/link[30]/link[31]/link[32]/link[33]/link[34]/link[35]/link[36]/link[37]/link[38]/link[39]/link[40]/link[41]/body[1]/img[1]/img[2]/img[3]/img[4]/img[5]/img[6]/img[7]/img[8]/img[9]/img[10]/img[11]/img[12]/img[13]/img[14]/img[15]/img[16]/img[17]/div[28]/header[2]/div[32]/div[63]/div[64]/div[66]/div[67]/div[71]/main[1]/div[72]/section[2]/div[108]/div[109]/div[110]/div[158]/div[159]/div[160]/ul[5]/li[27]/div[161]/li[28]/div[173]/li[29]/div[185]/li[30]/div[197]/li[31]/div[209]/li[32]/div[221]/li[33]/div[233]/li[34]/div[245]/li[35]/div[257]/li[36]/div[269]/li[37]/div[281]/li[38]/div[293]/li[39]/div[305]/li[40]/div[317]/li[41]/div[329]/li[42]/div[341]/li[43]/div[353]/li[44]/div[365]/li[45]/div[377]/li[46]/div[389]/li[47]/div[401]/li[48]/div[415]/li[49]/div[427]/li[50]/div[439]/li[51]/div[451]/li[52]/div[463]/li[53]/div[475]/li[54]/div[487]/li[55]/div[499]/section[32]/img[77]/div[500]/div[501]/div[502]/div[503]/div[506]",
|
|
"html_file": "/Volumes/KINGSTON/data/glam/data/custodian/person/affiliated/manual/(7) Noord-Hollands Archief_ People _ LinkedIn.html",
|
|
"xpath_match_score": 1.0,
|
|
"retrieval_agent": "extract_persons_with_provenance.py"
|
|
},
|
|
{
|
|
"claim_type": "headline",
|
|
"claim_value": "hoofd publiek Noord-Hollands Archief",
|
|
"source_url": "https://www.linkedin.com/company/noord-hollands-archief/people/",
|
|
"retrieved_on": "2025-12-12T21:58:47.350000+00:00",
|
|
"statement_created_at": "2026-01-09T22:45:50.810381+00:00",
|
|
"source_archived_at": "2025-12-12T21:58:47.350000+00:00",
|
|
"xpath": "/html[1]/head[1]/meta[1]/meta[2]/meta[3]/meta[4]/meta[5]/meta[6]/meta[7]/meta[8]/meta[9]/meta[10]/meta[11]/meta[12]/meta[13]/meta[14]/link[1]/link[2]/link[3]/link[4]/link[5]/link[6]/link[7]/meta[15]/meta[16]/meta[17]/meta[18]/meta[19]/meta[20]/meta[21]/meta[22]/meta[23]/meta[24]/meta[25]/meta[26]/link[8]/link[9]/link[10]/link[11]/link[12]/meta[27]/meta[28]/meta[29]/meta[30]/meta[31]/meta[32]/meta[33]/meta[34]/meta[35]/meta[36]/meta[37]/meta[38]/meta[39]/meta[40]/meta[41]/meta[42]/meta[43]/meta[44]/meta[45]/meta[46]/meta[47]/meta[48]/meta[49]/meta[50]/meta[51]/meta[52]/meta[53]/meta[54]/meta[55]/meta[56]/meta[57]/meta[58]/meta[59]/meta[60]/meta[61]/meta[62]/meta[63]/meta[64]/meta[65]/meta[66]/meta[67]/meta[68]/meta[69]/meta[70]/meta[71]/meta[72]/meta[73]/meta[74]/meta[75]/meta[76]/meta[77]/meta[78]/meta[79]/meta[80]/meta[81]/meta[82]/meta[83]/meta[84]/meta[85]/meta[86]/meta[87]/meta[88]/meta[89]/meta[90]/meta[91]/meta[92]/meta[93]/meta[94]/meta[95]/meta[96]/meta[97]/meta[98]/meta[99]/meta[100]/meta[101]/meta[102]/meta[103]/meta[104]/meta[105]/meta[106]/meta[107]/meta[108]/meta[109]/meta[110]/meta[111]/meta[112]/meta[113]/meta[114]/meta[115]/meta[116]/meta[117]/meta[118]/meta[119]/meta[120]/meta[121]/meta[122]/meta[123]/meta[124]/meta[125]/meta[126]/meta[127]/meta[128]/meta[129]/meta[130]/meta[131]/meta[132]/meta[133]/meta[134]/meta[135]/meta[136]/meta[137]/meta[138]/meta[139]/meta[140]/meta[141]/link[13]/link[14]/meta[142]/meta[143]/link[15]/link[16]/link[17]/link[18]/link[19]/link[20]/link[21]/link[22]/link[23]/link[24]/link[25]/link[26]/link[27]/link[28]/link[29]/link[30]/link[31]/link[32]/link[33]/link[34]/link[35]/link[36]/link[37]/link[38]/link[39]/link[40]/link[41]/body[1]/img[1]/img[2]/img[3]/img[4]/img[5]/img[6]/img[7]/img[8]/img[9]/img[10]/img[11]/img[12]/img[13]/img[14]/img[15]/img[16]/img[17]/div[28]/header[2]/div[32]/div[63]/div[64]/div[66]/div[67]/div[71]/main[1]/div[72]/section[2]/div[108]/div[109]/div[110]/div[158]/div[159]/div[160]/ul[5]/li[27]/div[161]/li[28]/div[173]/li[29]/div[185]/li[30]/div[197]/li[31]/div[209]/li[32]/div[221]/li[33]/div[233]/li[34]/div[245]/li[35]/div[257]/li[36]/div[269]/li[37]/div[281]/li[38]/div[293]/li[39]/div[305]/li[40]/div[317]/li[41]/div[329]/li[42]/div[341]/li[43]/div[353]/li[44]/div[365]/li[45]/div[377]/li[46]/div[389]/li[47]/div[401]/li[48]/div[415]/li[49]/div[427]/li[50]/div[439]/li[51]/div[451]/li[52]/div[463]/li[53]/div[475]/li[54]/div[487]/li[55]/div[499]/section[32]/img[77]/div[500]/div[501]/div[502]/div[503]/div[507]/div[508]/div[509]",
|
|
"html_file": "/Volumes/KINGSTON/data/glam/data/custodian/person/affiliated/manual/(7) Noord-Hollands Archief_ People _ LinkedIn.html",
|
|
"xpath_match_score": 1.0,
|
|
"retrieval_agent": "extract_persons_with_provenance.py"
|
|
}
|
|
],
|
|
"source_observations": [
|
|
{
|
|
"source_file": "/Users/kempersc/apps/glam/data/custodian/person/entity/annabelle-arntz-18903057_20251214T102713Z.json",
|
|
"observed_on": "2025-12-14T10:27:13.982390+00:00",
|
|
"extraction_agent": "claude-sonnet-4-20250514"
|
|
}
|
|
],
|
|
"enrichment_metadata": {
|
|
"birth_date_search": {
|
|
"attempted": false,
|
|
"notes": "Not yet searched - requires manual enrichment"
|
|
},
|
|
"deep_enrichment": {
|
|
"performed_on": "2026-01-11T00:00:00Z",
|
|
"performed_by": "opencode-claude-sonnet-4",
|
|
"sources_consulted": [
|
|
"https://www.linkedin.com/in/annabelle-arntz-18903057",
|
|
"https://noord-hollandsarchief.nl/over-ons/organisatie/mt"
|
|
],
|
|
"claims_added": 0,
|
|
"notes": "Added heritage_relevance.score (0.82) with detailed rationale. Hoofd Publiek at NHA since Jan 2024, previously Hoofd Communicatie (2020-2024). 7+ years at NHA total. Background in cultural communication at Duitsland Instituut Amsterdam. Education in German studies. 23+ years total experience."
|
|
}
|
|
},
|
|
"provenance": {
|
|
"created_at": "2026-01-09T17:29:48.571697+00:00",
|
|
"created_by": "generate_ppids.py",
|
|
"source_files": [
|
|
"/Users/kempersc/apps/glam/data/custodian/person/entity/annabelle-arntz-18903057_20251214T102713Z.json"
|
|
],
|
|
"modified_at": "2026-01-11T00:00:00Z",
|
|
"modified_by": "opencode-claude-sonnet-4",
|
|
"modification_notes": "Deep enrichment: Added heritage_relevance.score (0.82), deep_enrichment metadata block"
|
|
},
|
|
"linkedin_slug": "annabelle-arntz-18903057",
|
|
"ppid_history": [
|
|
{
|
|
"previous_ppid": "ID_XX-XX-XXX_XXXX_XX-XX-XXX_XXXX_ANNABELLE-ARNTZ",
|
|
"new_ppid": "ID_XX-XX-XXX_198X_NL-NH-AMS_XXXX_ANNABELLE-ARNTZ",
|
|
"changed_at": "2026-01-09T17:43:00.470332+00:00",
|
|
"reason": "observation_based_inference",
|
|
"inferred_fields": [
|
|
"inferred_birth_decade",
|
|
"inferred_current_settlement"
|
|
]
|
|
},
|
|
{
|
|
"previous_ppid": "ID_XX-XX-XXX_198X_NL-NH-AMS_XXXX_ANNABELLE-ARNTZ",
|
|
"new_ppid": "ID_NL-GE-EDE_198X_NL-NH-AMS_XXXX_ANNABELLE-ARNTZ",
|
|
"changed_at": "2026-01-09T19:15:36.450241+00:00",
|
|
"reason": "observation_based_inference",
|
|
"inferred_fields": [
|
|
"inferred_birth_decade",
|
|
"inferred_birth_settlement"
|
|
]
|
|
},
|
|
{
|
|
"previous_ppid": "ID_NL-GE-EDE_198X_NL-NH-AMS_XXXX_ANNABELLE-ARNTZ",
|
|
"new_ppid": "ID_NL-GE-EDE_197X_NL-NH-AMS_XXXX_ANNABELLE-ARNTZ",
|
|
"changed_at": "2026-01-09T19:18:14.208406+00:00",
|
|
"reason": "observation_based_inference",
|
|
"inferred_fields": [
|
|
"inferred_birth_decade"
|
|
]
|
|
}
|
|
],
|
|
"inferred_birth_decade": {
|
|
"value": "197X",
|
|
"edtf": "197X",
|
|
"precision": "decade",
|
|
"confidence": "low",
|
|
"inference_provenance": {
|
|
"method": "earliest_education_heuristic",
|
|
"inference_chain": [
|
|
{
|
|
"step": 1,
|
|
"observation": "Education record found",
|
|
"source_field": "profile_data.education",
|
|
"source_value": {
|
|
"institution": "Westfälische Wilhelms-Universität Münster",
|
|
"degree": "Master of Arts (M.A.), Magister Nederlands, Duits, Niederlande-Studien",
|
|
"date_range": "1998 - 2005 • 7 years"
|
|
}
|
|
},
|
|
{
|
|
"step": 2,
|
|
"extraction": "Start year extracted from date_range",
|
|
"extracted_value": 1998
|
|
},
|
|
{
|
|
"step": 3,
|
|
"assumption": "Education entry age is approximately 22 (±3 years)",
|
|
"rationale": "Standard entry age for this education level in Netherlands/Europe",
|
|
"confidence_impact": "Assumption introduces uncertainty; actual age may vary ±3 years"
|
|
},
|
|
{
|
|
"step": 4,
|
|
"calculation": "1998 - 22 = 1976",
|
|
"result": "Estimated birth year: 1976",
|
|
"range": "1973-1979 (accounting for ±3 year variance)"
|
|
},
|
|
{
|
|
"step": 5,
|
|
"generalization": "Convert to EDTF decade notation",
|
|
"input": 1976,
|
|
"output": "197X",
|
|
"rationale": "Decade precision appropriate for heuristic-based estimate"
|
|
}
|
|
],
|
|
"assumptions": [
|
|
"Entry age for education/first job: 22 years (±3)",
|
|
"Career records are complete in LinkedIn profile"
|
|
],
|
|
"inferred_at": "2026-01-09T19:51:18.735289+00:00",
|
|
"inferred_by": "enrich_ppids.py"
|
|
}
|
|
},
|
|
"extraction_provenance": {
|
|
"source_files": [
|
|
"/Users/kempersc/apps/glam/data/custodian/person/affiliated/parsed/missing_entity_profiles.json",
|
|
"(7) Noord-Hollands Archief_ People _ LinkedIn.html"
|
|
],
|
|
"modified_at": "2026-01-10T12:56:38.042650+00:00",
|
|
"modified_by": "process_entity_to_ppid.py"
|
|
}
|
|
} |