767fb8ca80
Person Identity Classes: - PersonName: Full name modeling with components (given_name, surname_prefix, base_surname, patronym, initials) following Dutch naming conventions - PersonConnection: Professional network connections with heritage relevance scoring - ConnectionNetwork: Network-level analysis and statistics LinkedIn Profile Schema: - LinkedInProfile: Complete professional profile structure - WorkExperience: Employment history with heritage institution detection - EducationCredential: Academic background and qualifications - LanguageProficiency: Language skills with ISO 639-1 codes Supporting Classes: - ExtractionMetadata: Provenance tracking for extracted profile data - HeritageRelevance: GLAMORCUBESFIXPHDNT type scoring and classification Slots (17 person-related slots): - Name components: given_name, base_surname, surname_prefix, patronym, initials - Identity: age, birth_date, birth_place, death_place, gender_identity, pronouns - Professional: occupation, religion - References: literal_name, name_specification, has_person_name, extraction_metadata Enums: - HeritageTypeEnum: GLAMORCUBESFIXPHDNT type codes for heritage relevance
612 lines
18 KiB
YAML
612 lines
18 KiB
YAML
# LinkedIn Profile Class
|
|
# Complete LinkedIn profile extraction for person entity files
|
|
|
|
id: https://nde.nl/ontology/hc/class/LinkedInProfile
|
|
name: linkedin_profile_class
|
|
title: LinkedIn Profile Class
|
|
version: 1.0.0
|
|
|
|
prefixes:
|
|
linkml: https://w3id.org/linkml/
|
|
hc: https://nde.nl/ontology/hc/
|
|
schema: http://schema.org/
|
|
foaf: http://xmlns.com/foaf/0.1/
|
|
prov: http://www.w3.org/ns/prov#
|
|
dct: http://purl.org/dc/terms/
|
|
|
|
imports:
|
|
- linkml:types
|
|
- ../metadata
|
|
- ./ExtractionMetadata
|
|
- ./WorkExperience
|
|
- ./EducationCredential
|
|
- ./HeritageRelevance
|
|
- ./LanguageProficiency
|
|
|
|
default_range: string
|
|
|
|
classes:
|
|
|
|
LinkedInProfile:
|
|
class_uri: schema:ProfilePage
|
|
description: |
|
|
Complete LinkedIn profile extraction for a person.
|
|
|
|
Models the content of person entity JSON files stored at
|
|
`data/custodian/person/entity/*.json`. This is the root class
|
|
for LinkedIn profile data extracted via Exa API or HTML parsing.
|
|
|
|
**Relationship to PersonObservation**:
|
|
- PersonObservation.linkedin_profile_path references the file containing
|
|
this LinkedInProfile data
|
|
- PersonObservation.linkedin_profile_url links to the source URL
|
|
- This class models the CONTENT of that file
|
|
|
|
**Relationship to SocialMediaProfile**:
|
|
- SocialMediaProfile (in same schema) is for CUSTODIAN social media accounts
|
|
(e.g., Rijksmuseum's Instagram, Nationaal Archief's Twitter)
|
|
- LinkedInProfile is for PERSON LinkedIn profiles (staff members)
|
|
- These are complementary, not overlapping classes
|
|
|
|
**Data Flow**:
|
|
```
|
|
LinkedIn URL → Exa API → JSON file → LinkedInProfile (this class)
|
|
↑
|
|
PersonObservation.linkedin_profile_path references this file
|
|
```
|
|
|
|
**Example JSON Structure**:
|
|
```json
|
|
{
|
|
"extraction_metadata": {
|
|
"source_file": "...",
|
|
"staff_id": "org_staff_0001_name",
|
|
"extraction_date": "2025-12-12T22:00:00Z",
|
|
"extraction_method": "exa_crawling_exa",
|
|
"extraction_agent": "claude-opus-4.5",
|
|
"linkedin_url": "https://www.linkedin.com/in/...",
|
|
"cost_usd": 0.001
|
|
},
|
|
"profile_data": {
|
|
"name": "Sander Hulleman",
|
|
"headline": "Stafadviseur PO",
|
|
"location": "Arnhem, Gelderland, Netherlands",
|
|
"connections": "246 connections • 248 followers",
|
|
"about": "Third year student...",
|
|
"experience": [...],
|
|
"education": [...],
|
|
"skills": ["education"],
|
|
"languages": ["English - Native or bilingual"],
|
|
"profile_image_url": "https://media.licdn.com/..."
|
|
},
|
|
"heritage_relevance": {
|
|
"is_heritage_relevant": true,
|
|
"heritage_types": ["E"],
|
|
"rationale": "Education sector professional..."
|
|
},
|
|
"source_organization": "the-dutch-inspectorate-of-education",
|
|
"whatsapp_enrichment": {...}
|
|
}
|
|
```
|
|
|
|
tree_root: true
|
|
|
|
exact_mappings:
|
|
- schema:ProfilePage
|
|
close_mappings:
|
|
- foaf:PersonalProfileDocument
|
|
- schema:Person
|
|
|
|
slots:
|
|
- extraction_metadata
|
|
- profile_data
|
|
- heritage_relevance
|
|
- source_organization
|
|
- whatsapp_enrichment
|
|
|
|
slot_usage:
|
|
extraction_metadata:
|
|
description: |
|
|
Provenance metadata for the extraction activity.
|
|
Records how, when, and by what agent this profile was extracted.
|
|
See ExtractionMetadata class for field definitions.
|
|
range: ExtractionMetadata
|
|
required: true
|
|
inlined: true
|
|
|
|
profile_data:
|
|
description: |
|
|
Core profile data extracted from LinkedIn.
|
|
Contains personal info, career history, education, skills, languages.
|
|
See LinkedInProfileData class for field definitions.
|
|
range: LinkedInProfileData
|
|
required: true
|
|
inlined: true
|
|
|
|
heritage_relevance:
|
|
description: |
|
|
Classification of this person's relevance to heritage sectors.
|
|
See HeritageRelevance class for scoring guidelines.
|
|
range: HeritageRelevance
|
|
inlined: true
|
|
|
|
source_organization:
|
|
description: |
|
|
Slug identifier of the organization from which this profile was discovered.
|
|
Matches the custodian slug used in staff list parsing.
|
|
Format: lowercase with hyphens (e.g., "rijksmuseum", "nationaal-archief")
|
|
slot_uri: prov:wasInfluencedBy
|
|
range: string
|
|
pattern: "^[a-z0-9-]+$"
|
|
examples:
|
|
- value: "the-dutch-inspectorate-of-education"
|
|
description: "Organization where person was discovered as staff"
|
|
- value: "rijksmuseum"
|
|
description: "Heritage institution employer"
|
|
|
|
whatsapp_enrichment:
|
|
description: |
|
|
Optional WhatsApp business likelihood enrichment.
|
|
Added by enrichment scripts to assess digital communication capabilities.
|
|
range: WhatsAppEnrichment
|
|
inlined: true
|
|
|
|
comments:
|
|
- "This is the root class for person entity JSON files"
|
|
- "PersonObservation.linkedin_profile_path references files containing this data"
|
|
- "See AGENTS.md Rule 20 for person entity file requirements"
|
|
- "See AGENTS.md Rule 27 for person-custodian data architecture"
|
|
|
|
see_also:
|
|
- "https://schema.org/ProfilePage"
|
|
- "https://nde.nl/ontology/hc/class/PersonObservation"
|
|
- "https://nde.nl/ontology/hc/class/SocialMediaProfile"
|
|
|
|
LinkedInProfileData:
|
|
class_uri: schema:Person
|
|
description: |
|
|
Core profile data extracted from a LinkedIn profile.
|
|
|
|
Contains the person's professional information including:
|
|
- Basic info (name, headline, location, connections)
|
|
- About/summary text
|
|
- Career history (experience array)
|
|
- Education history (education array)
|
|
- Skills and languages
|
|
- Profile image URL
|
|
|
|
**Note on Data Representation**:
|
|
- Raw strings are preserved for provenance (e.g., connections text)
|
|
- Nested objects use defined classes (WorkExperience, EducationCredential)
|
|
- Skills are simple strings (not structured objects)
|
|
- Languages may be raw strings or LanguageProficiency objects
|
|
|
|
exact_mappings:
|
|
- schema:Person
|
|
close_mappings:
|
|
- foaf:Person
|
|
|
|
slots:
|
|
- profile_name
|
|
- profile_linkedin_url
|
|
- headline
|
|
- profile_location
|
|
- connections_text
|
|
- about_text
|
|
- experience
|
|
- education
|
|
- skills
|
|
- languages_raw
|
|
- languages
|
|
- profile_image_url
|
|
|
|
slot_usage:
|
|
profile_name:
|
|
description: |
|
|
Full name of the person as displayed on LinkedIn.
|
|
slot_uri: schema:name
|
|
range: string
|
|
required: true
|
|
examples:
|
|
- value: "Sander Hulleman"
|
|
- value: "Jan van der Berg"
|
|
|
|
profile_linkedin_url:
|
|
description: |
|
|
LinkedIn profile URL for this person.
|
|
Duplicated from extraction_metadata for convenience.
|
|
slot_uri: schema:url
|
|
range: uri
|
|
pattern: "^https://www\\.linkedin\\.com/in/[a-z0-9-]+/?$"
|
|
examples:
|
|
- value: "https://www.linkedin.com/in/sander-hulleman-5017b9105"
|
|
|
|
headline:
|
|
description: |
|
|
Professional headline/tagline from LinkedIn.
|
|
Typically includes current job title and/or professional identity.
|
|
slot_uri: schema:jobTitle
|
|
range: string
|
|
examples:
|
|
- value: "Stafadviseur PO"
|
|
description: "Dutch job title"
|
|
- value: "Senior Curator | Rijksmuseum"
|
|
description: "Title with organization"
|
|
- value: "Digital Archivist | Heritage Data Specialist"
|
|
description: "Multiple roles"
|
|
|
|
profile_location:
|
|
description: |
|
|
Location as displayed on LinkedIn profile.
|
|
Format varies: "City, Region, Country" or "City, Country"
|
|
slot_uri: schema:homeLocation
|
|
range: string
|
|
examples:
|
|
- value: "Arnhem, Gelderland, Netherlands"
|
|
- value: "Amsterdam, Netherlands"
|
|
|
|
connections_text:
|
|
description: |
|
|
Raw connections/followers text from LinkedIn.
|
|
Format: "X connections • Y followers"
|
|
Preserved as-is for provenance.
|
|
slot_uri: schema:description
|
|
range: string
|
|
examples:
|
|
- value: "246 connections • 248 followers"
|
|
- value: "500+ connections"
|
|
|
|
about_text:
|
|
description: |
|
|
About/summary section text from LinkedIn profile.
|
|
May be absent if person hasn't written a summary.
|
|
slot_uri: schema:description
|
|
range: string
|
|
examples:
|
|
- value: "Third year student at Stenden University..."
|
|
|
|
experience:
|
|
description: |
|
|
Work experience entries from LinkedIn.
|
|
Array of WorkExperience objects with job title, company, dates, location.
|
|
range: WorkExperience
|
|
multivalued: true
|
|
inlined_as_list: true
|
|
|
|
education:
|
|
description: |
|
|
Education entries from LinkedIn.
|
|
Array of EducationCredential objects with school, degree, years.
|
|
range: EducationCredential
|
|
multivalued: true
|
|
inlined_as_list: true
|
|
|
|
skills:
|
|
description: |
|
|
Skills listed on LinkedIn profile.
|
|
Simple string array (not structured objects).
|
|
slot_uri: schema:knowsAbout
|
|
range: string
|
|
multivalued: true
|
|
examples:
|
|
- value: ["education", "teaching", "curriculum development"]
|
|
|
|
languages_raw:
|
|
description: |
|
|
Raw language strings as extracted from LinkedIn.
|
|
Format: "Language - Proficiency level"
|
|
Use this when storing unprocessed data.
|
|
range: string
|
|
multivalued: true
|
|
examples:
|
|
- value: ["English - Native or bilingual", "Dutch - Native or bilingual"]
|
|
|
|
languages:
|
|
description: |
|
|
Parsed language proficiency entries.
|
|
Array of LanguageProficiency objects with language name, code, level.
|
|
Use this when storing processed/structured data.
|
|
range: LanguageProficiency
|
|
multivalued: true
|
|
inlined_as_list: true
|
|
|
|
profile_image_url:
|
|
description: |
|
|
URL to the LinkedIn profile photo.
|
|
Should be the actual CDN URL (media.licdn.com), not overlay page.
|
|
See AGENTS.md Rule 16 for photo URL requirements.
|
|
slot_uri: schema:image
|
|
range: uri
|
|
pattern: "^https://media\\.licdn\\.com/.*$"
|
|
examples:
|
|
- value: "https://media.licdn.com/dms/image/v2/C4E03AQHoGyR6G0kphA/profile-displayphoto-shrink_200_200/..."
|
|
|
|
comments:
|
|
- "Inlined within LinkedInProfile as profile_data"
|
|
- "experience and education use inlined_as_list for JSON array representation"
|
|
- "languages_raw preserves original strings; languages has parsed objects"
|
|
- "profile_image_url must be CDN URL per AGENTS.md Rule 16"
|
|
|
|
WhatsAppEnrichment:
|
|
class_uri: hc:WhatsAppEnrichment
|
|
description: |
|
|
WhatsApp business likelihood enrichment data.
|
|
|
|
Added by enrichment scripts to assess whether a person is likely
|
|
to use WhatsApp for professional/business communication.
|
|
|
|
**Assessment Factors**:
|
|
- Digital technology indicators in profile
|
|
- Role type (customer-facing, technical, etc.)
|
|
- Industry/sector norms
|
|
- Geographic region (WhatsApp prevalence varies)
|
|
|
|
slots:
|
|
- digital_professional
|
|
- whatsapp_business_likelihood
|
|
- enrichment_metadata_whatsapp
|
|
|
|
slot_usage:
|
|
digital_professional:
|
|
description: |
|
|
Assessment of digital/technology proficiency.
|
|
range: DigitalProfessionalAssessment
|
|
inlined: true
|
|
|
|
whatsapp_business_likelihood:
|
|
description: |
|
|
Likelihood score for WhatsApp business usage.
|
|
range: WhatsAppLikelihood
|
|
inlined: true
|
|
|
|
enrichment_metadata_whatsapp:
|
|
description: |
|
|
Metadata about the enrichment process.
|
|
range: WhatsAppEnrichmentMetadata
|
|
inlined: true
|
|
|
|
DigitalProfessionalAssessment:
|
|
class_uri: hc:DigitalProfessionalAssessment
|
|
description: |
|
|
Assessment of a person's digital/technology proficiency.
|
|
slots:
|
|
- likely_whatsapp_proficient
|
|
- digital_indicators
|
|
- digital_confidence
|
|
|
|
slot_usage:
|
|
likely_whatsapp_proficient:
|
|
description: "Whether person is likely proficient with WhatsApp"
|
|
range: boolean
|
|
|
|
digital_indicators:
|
|
description: "Indicators of digital proficiency from profile"
|
|
range: string
|
|
multivalued: true
|
|
|
|
digital_confidence:
|
|
description: "Confidence level: low, medium, high"
|
|
range: string
|
|
|
|
WhatsAppLikelihood:
|
|
class_uri: hc:WhatsAppLikelihood
|
|
description: |
|
|
Likelihood score for WhatsApp business usage.
|
|
slots:
|
|
- likelihood_score
|
|
- max_likelihood_score
|
|
- likelihood_level
|
|
- likelihood_confidence
|
|
- likelihood_factors
|
|
- assessment_date
|
|
|
|
slot_usage:
|
|
likelihood_score:
|
|
description: "Numeric score (0-100)"
|
|
range: integer
|
|
minimum_value: 0
|
|
maximum_value: 100
|
|
|
|
max_likelihood_score:
|
|
description: "Maximum possible score (typically 100)"
|
|
range: integer
|
|
|
|
likelihood_level:
|
|
description: "Categorical level: low, medium, high"
|
|
range: string
|
|
|
|
likelihood_confidence:
|
|
description: "Confidence in the assessment (0.0-1.0)"
|
|
range: float
|
|
minimum_value: 0.0
|
|
maximum_value: 1.0
|
|
|
|
likelihood_factors:
|
|
description: "Factors contributing to the score"
|
|
range: string
|
|
multivalued: true
|
|
|
|
assessment_date:
|
|
description: "When the assessment was performed (ISO 8601)"
|
|
range: datetime
|
|
|
|
WhatsAppEnrichmentMetadata:
|
|
class_uri: hc:WhatsAppEnrichmentMetadata
|
|
description: |
|
|
Metadata about the WhatsApp enrichment process.
|
|
slots:
|
|
- enriched_date
|
|
- enrichment_method_whatsapp
|
|
- data_source_whatsapp
|
|
- no_fabrication
|
|
- all_data_real
|
|
|
|
slot_usage:
|
|
enriched_date:
|
|
description: "When enrichment was performed (ISO 8601)"
|
|
range: datetime
|
|
|
|
enrichment_method_whatsapp:
|
|
description: "Method used for enrichment"
|
|
range: string
|
|
examples:
|
|
- value: "linkedin_profile_analysis"
|
|
|
|
data_source_whatsapp:
|
|
description: "Source of data for enrichment"
|
|
range: string
|
|
examples:
|
|
- value: "public_linkedin_profile"
|
|
|
|
no_fabrication:
|
|
description: "Confirms no data was fabricated"
|
|
range: boolean
|
|
|
|
all_data_real:
|
|
description: "Confirms all data is from real sources"
|
|
range: boolean
|
|
|
|
# Top-level slot definitions
|
|
slots:
|
|
extraction_metadata:
|
|
description: "Provenance metadata for the extraction activity"
|
|
range: ExtractionMetadata
|
|
|
|
profile_data:
|
|
description: "Core profile data from LinkedIn"
|
|
range: LinkedInProfileData
|
|
|
|
heritage_relevance:
|
|
description: "Heritage sector classification"
|
|
range: HeritageRelevance
|
|
|
|
source_organization:
|
|
description: "Organization slug where person was discovered"
|
|
range: string
|
|
|
|
whatsapp_enrichment:
|
|
description: "WhatsApp business likelihood enrichment"
|
|
range: WhatsAppEnrichment
|
|
|
|
profile_name:
|
|
description: "Full name of the person"
|
|
range: string
|
|
|
|
profile_linkedin_url:
|
|
description: "LinkedIn profile URL"
|
|
range: uri
|
|
|
|
headline:
|
|
description: "Professional headline/tagline"
|
|
range: string
|
|
|
|
profile_location:
|
|
description: "Location as displayed on profile"
|
|
range: string
|
|
|
|
connections_text:
|
|
description: "Raw connections/followers text"
|
|
range: string
|
|
|
|
about_text:
|
|
description: "About/summary section text"
|
|
range: string
|
|
|
|
experience:
|
|
description: "Work experience entries"
|
|
range: WorkExperience
|
|
multivalued: true
|
|
|
|
education:
|
|
description: "Education entries"
|
|
range: EducationCredential
|
|
multivalued: true
|
|
|
|
skills:
|
|
description: "Skills listed on profile"
|
|
range: string
|
|
multivalued: true
|
|
|
|
languages_raw:
|
|
description: "Raw language strings"
|
|
range: string
|
|
multivalued: true
|
|
|
|
languages:
|
|
description: "Parsed language proficiency entries"
|
|
range: LanguageProficiency
|
|
multivalued: true
|
|
|
|
profile_image_url:
|
|
description: "Profile photo URL"
|
|
range: uri
|
|
|
|
digital_professional:
|
|
description: "Digital proficiency assessment"
|
|
range: DigitalProfessionalAssessment
|
|
|
|
whatsapp_business_likelihood:
|
|
description: "WhatsApp business usage likelihood"
|
|
range: WhatsAppLikelihood
|
|
|
|
enrichment_metadata_whatsapp:
|
|
description: "WhatsApp enrichment metadata"
|
|
range: WhatsAppEnrichmentMetadata
|
|
|
|
likely_whatsapp_proficient:
|
|
description: "Whether person is likely WhatsApp proficient"
|
|
range: boolean
|
|
|
|
digital_indicators:
|
|
description: "Indicators of digital proficiency"
|
|
range: string
|
|
multivalued: true
|
|
|
|
digital_confidence:
|
|
description: "Digital proficiency confidence level"
|
|
range: string
|
|
|
|
likelihood_score:
|
|
description: "Numeric likelihood score"
|
|
range: integer
|
|
|
|
max_likelihood_score:
|
|
description: "Maximum possible score"
|
|
range: integer
|
|
|
|
likelihood_level:
|
|
description: "Categorical likelihood level"
|
|
range: string
|
|
|
|
likelihood_confidence:
|
|
description: "Confidence in the assessment"
|
|
range: float
|
|
|
|
likelihood_factors:
|
|
description: "Factors contributing to score"
|
|
range: string
|
|
multivalued: true
|
|
|
|
assessment_date:
|
|
description: "When assessment was performed"
|
|
range: datetime
|
|
|
|
enriched_date:
|
|
description: "When enrichment was performed"
|
|
range: datetime
|
|
|
|
enrichment_method_whatsapp:
|
|
description: "Method used for enrichment"
|
|
range: string
|
|
|
|
data_source_whatsapp:
|
|
description: "Data source for enrichment"
|
|
range: string
|
|
|
|
no_fabrication:
|
|
description: "Confirms no data was fabricated"
|
|
range: boolean
|
|
|
|
all_data_real:
|
|
description: "Confirms all data is real"
|
|
range: boolean
|