4322 lines
163 KiB
YAML
4322 lines
163 KiB
YAML
# =============================================================================
|
||
# GLAM-NER Entity Annotation Convention v1.7.0
|
||
# Module: integrations/pico.yaml
|
||
# =============================================================================
|
||
# PiCO (Person in Context Ontology) integration for person observation modeling.
|
||
# Enables tracking provenance of person mentions and linking to formal records.
|
||
#
|
||
# Key concepts:
|
||
# - PersonObservation: A textual mention of a person (source-bound)
|
||
# - PersonName (PNV): Structured name components
|
||
# - Person (CIDOC-CRM E21): Reconstructed person entity
|
||
#
|
||
# References:
|
||
# - PiCo Ontology: https://w3id.org/pico
|
||
# - Person Name Vocabulary (PNV): https://w3id.org/pnv
|
||
# - CIDOC-CRM: https://www.cidoc-crm.org/
|
||
# =============================================================================
|
||
|
||
pico_integration:
|
||
|
||
description: |
|
||
PiCO (Person in Context Ontology) models textual observations of persons
|
||
as distinct from reconstructed person entities. This enables:
|
||
- Tracking provenance of person mentions
|
||
- Handling name variations across sources
|
||
- Linking observations to formal person records
|
||
|
||
The observation/reconstruction pattern separates:
|
||
1. What was OBSERVED in text (PersonObservation) - source-bound, exact
|
||
2. What was RECONSTRUCTED as entity (E21_Person) - inferred, normalized
|
||
|
||
This is critical for heritage data where the same person may appear with
|
||
different name forms, titles, or spellings across sources.
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Core Observation Pattern
|
||
# ---------------------------------------------------------------------------
|
||
|
||
observation_pattern:
|
||
description: "Every person mention creates a PersonObservation"
|
||
class: "picom:PersonObservation"
|
||
class_uri: "https://w3id.org/pico/PersonObservation"
|
||
|
||
properties:
|
||
- property: "picom:hasObservedName"
|
||
description: "The name string as it appears in text"
|
||
range: "pnv:PersonName"
|
||
cardinality: "1"
|
||
note: "Exact transcription of name from source"
|
||
|
||
- property: "picom:isObservationOf"
|
||
description: "Links to reconstructed Person entity"
|
||
range: "crm:E21_Person"
|
||
cardinality: "0..1"
|
||
note: "May be null if person not yet identified"
|
||
|
||
- property: "prov:hadPrimarySource"
|
||
description: "The source document/webpage"
|
||
range: "prov:Entity"
|
||
cardinality: "1"
|
||
note: "Required for provenance tracking"
|
||
|
||
- property: "picom:observedAt"
|
||
description: "When the observation was made"
|
||
range: "xsd:dateTime"
|
||
cardinality: "1"
|
||
note: "Extraction timestamp, not document date"
|
||
|
||
- property: "picom:observedInContext"
|
||
description: "Surrounding text context"
|
||
range: "xsd:string"
|
||
cardinality: "0..1"
|
||
note: "For disambiguation when reviewing"
|
||
|
||
- property: "picom:hasRole"
|
||
description: "Role/position observed with the person"
|
||
range: "xsd:string"
|
||
cardinality: "0..*"
|
||
note: "Links to ROLE hypernym when extracted"
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Person Name Vocabulary (PNV)
|
||
# ---------------------------------------------------------------------------
|
||
|
||
pnv_name_structure:
|
||
description: |
|
||
Person Name Vocabulary (PNV) provides structured name components.
|
||
This enables proper parsing of complex name structures across cultures.
|
||
|
||
class: "pnv:PersonName"
|
||
class_uri: "https://w3id.org/pnv/PersonName"
|
||
|
||
components:
|
||
- property: "pnv:literalName"
|
||
description: "Full name as single string"
|
||
examples:
|
||
- "Dr. Maria van den Berg"
|
||
- "Rembrandt Harmenszoon van Rijn"
|
||
- "Queen Elizabeth II"
|
||
note: "Original string before parsing"
|
||
|
||
- property: "pnv:givenName"
|
||
description: "First/given name"
|
||
examples:
|
||
- "Rembrandt"
|
||
- "Maria"
|
||
- "Jan"
|
||
- "Elizabeth"
|
||
note: "Personal name, not surname"
|
||
|
||
- property: "pnv:patronym"
|
||
description: "Patronymic name component"
|
||
examples:
|
||
- "Harmenszoon"
|
||
- "Janszoon"
|
||
- "Pietersdochter"
|
||
note: "Common in Dutch, Scandinavian, Slavic names"
|
||
|
||
- property: "pnv:surnamePrefix"
|
||
description: "Prefix to surname (tussenvoegsel)"
|
||
examples:
|
||
- "van"
|
||
- "de"
|
||
- "van den"
|
||
- "van der"
|
||
- "op de"
|
||
- "'t"
|
||
- "von"
|
||
- "di"
|
||
note: "Language-specific, affects sorting"
|
||
|
||
- property: "pnv:baseSurname"
|
||
description: "Core surname without prefix"
|
||
examples:
|
||
- "Rijn"
|
||
- "Berg"
|
||
- "Velde"
|
||
- "Gogh"
|
||
note: "Primary sorting component in Dutch"
|
||
|
||
- property: "pnv:honorificPrefix"
|
||
description: "Title or honorific before name"
|
||
examples:
|
||
- "Dr."
|
||
- "Prof."
|
||
- "Prof. dr."
|
||
- "Sir"
|
||
- "Queen"
|
||
- "Mr."
|
||
- "Drs."
|
||
- "Ir."
|
||
note: "May indicate role - link to ROL"
|
||
|
||
- property: "pnv:honorificSuffix"
|
||
description: "Title or honorific after name"
|
||
examples:
|
||
- "PhD"
|
||
- "Jr."
|
||
- "III"
|
||
- "MD"
|
||
- "RA"
|
||
- "MSc"
|
||
note: "Credentials and generational markers"
|
||
|
||
- property: "pnv:infixTitle"
|
||
description: "Title within name structure"
|
||
examples:
|
||
- "graaf van"
|
||
- "baron de"
|
||
- "duke of"
|
||
note: "Nobility titles embedded in name"
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Dutch Name Conventions (Project-Specific)
|
||
# ---------------------------------------------------------------------------
|
||
|
||
dutch_name_patterns:
|
||
description: |
|
||
Special handling for Dutch names with tussenvoegsels (surname prefixes).
|
||
Dutch sorting rules differ from other languages.
|
||
|
||
tussenvoegsel_list:
|
||
- "van"
|
||
- "van de"
|
||
- "van den"
|
||
- "van der"
|
||
- "de"
|
||
- "den"
|
||
- "het"
|
||
- "'t"
|
||
- "ter"
|
||
- "ten"
|
||
- "op de"
|
||
- "op den"
|
||
- "in 't"
|
||
- "in de"
|
||
|
||
sorting_rule: |
|
||
In Dutch, surnames sort by baseSurname, ignoring tussenvoegsel.
|
||
"Vincent van Gogh" sorts under "G" not "V".
|
||
"Maria van den Berg" sorts under "B" not "V".
|
||
|
||
capitalization_rule: |
|
||
Tussenvoegsel lowercase when preceded by given name:
|
||
- "Vincent van Gogh" (not "Vincent Van Gogh")
|
||
- "Van Gogh" (surname alone, capitalized)
|
||
- "de heer Van Gogh" (formal, capitalized)
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Integration with GLAM-NER Hypernyms
|
||
# ---------------------------------------------------------------------------
|
||
|
||
hypernym_mapping:
|
||
description: "How PiCo concepts map to GLAM-NER v1.7.0 hypernyms"
|
||
|
||
mappings:
|
||
- pico_class: "picom:PersonObservation"
|
||
glam_hypernym: "AGT.PER"
|
||
glam_code: "AGT.PER"
|
||
note: "Person observations create AGT.PER entities"
|
||
|
||
- pico_class: "picom:PersonObservation"
|
||
glam_hypernym: "AGT.STF"
|
||
glam_code: "AGT.STF"
|
||
condition: "When observed with organizational role"
|
||
note: "Staff members with role context"
|
||
|
||
- pico_class: "pnv:PersonName"
|
||
glam_hypernym: "APP.NAM"
|
||
glam_code: "APP.NAM"
|
||
note: "Name strings as appellations"
|
||
|
||
- pico_class: "picom:hasRole"
|
||
glam_hypernym: "ROL"
|
||
glam_code: "ROL"
|
||
note: "Extracted roles link to ROL hypernym"
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Example Annotations
|
||
# ---------------------------------------------------------------------------
|
||
|
||
examples:
|
||
- description: "Staff member with title and role"
|
||
text: "Dr. Maria van den Berg, Director"
|
||
|
||
observation:
|
||
type: "picom:PersonObservation"
|
||
id: "_:obs1"
|
||
|
||
hasObservedName:
|
||
type: "pnv:PersonName"
|
||
literalName: "Dr. Maria van den Berg"
|
||
honorificPrefix: "Dr."
|
||
givenName: "Maria"
|
||
surnamePrefix: "van den"
|
||
baseSurname: "Berg"
|
||
|
||
hasRole: "Director"
|
||
hadPrimarySource: "https://example.org/staff-page"
|
||
observedAt: "2025-12-02T10:30:00Z"
|
||
|
||
glam_ner_annotations:
|
||
- span: "Dr. Maria van den Berg"
|
||
type: "AGT.STF"
|
||
code: "AGT.STF"
|
||
confidence: 0.95
|
||
|
||
- span: "Director"
|
||
type: "ROL.TIT"
|
||
code: "ROL.TIT"
|
||
confidence: 0.98
|
||
|
||
- description: "Historical artist"
|
||
text: "Rembrandt van Rijn painted this in 1642"
|
||
|
||
observation:
|
||
type: "picom:PersonObservation"
|
||
id: "_:obs2"
|
||
|
||
hasObservedName:
|
||
type: "pnv:PersonName"
|
||
literalName: "Rembrandt van Rijn"
|
||
givenName: "Rembrandt"
|
||
surnamePrefix: "van"
|
||
baseSurname: "Rijn"
|
||
|
||
isObservationOf: "wd:Q5598" # Wikidata Rembrandt
|
||
hadPrimarySource: "https://example.org/artwork-page"
|
||
observedAt: "2025-12-02T10:35:00Z"
|
||
|
||
glam_ner_annotations:
|
||
- span: "Rembrandt van Rijn"
|
||
type: "AGT.PER"
|
||
code: "AGT.PER"
|
||
confidence: 0.99
|
||
linking:
|
||
wikidata: "Q5598"
|
||
viaf: "64013650"
|
||
|
||
- description: "Nobility title"
|
||
text: "Count Willem van Loon"
|
||
|
||
observation:
|
||
type: "picom:PersonObservation"
|
||
id: "_:obs3"
|
||
|
||
hasObservedName:
|
||
type: "pnv:PersonName"
|
||
literalName: "Count Willem van Loon"
|
||
honorificPrefix: "Count"
|
||
givenName: "Willem"
|
||
surnamePrefix: "van"
|
||
baseSurname: "Loon"
|
||
|
||
hadPrimarySource: "https://example.org/archive-doc"
|
||
observedAt: "2025-12-02T10:40:00Z"
|
||
|
||
glam_ner_annotations:
|
||
- span: "Count Willem van Loon"
|
||
type: "AGT.PER"
|
||
code: "AGT.PER"
|
||
confidence: 0.95
|
||
|
||
- span: "Count"
|
||
type: "ROL.HON"
|
||
code: "ROL.HON"
|
||
note: "Nobility title - honorific role"
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Provenance Chain
|
||
# ---------------------------------------------------------------------------
|
||
|
||
provenance_model:
|
||
description: |
|
||
PiCo observations maintain full provenance chain:
|
||
|
||
Observation → Source Document → Extraction Activity → Agent
|
||
|
||
This enables:
|
||
- Tracking where each name form was found
|
||
- Attributing extractions to human/ML agents
|
||
- Maintaining audit trail for corrections
|
||
|
||
chain_structure:
|
||
observation:
|
||
class: "picom:PersonObservation"
|
||
properties:
|
||
- "prov:hadPrimarySource" # → Source document
|
||
- "prov:wasGeneratedBy" # → Extraction activity
|
||
|
||
source:
|
||
class: "prov:Entity"
|
||
properties:
|
||
- "prov:wasAttributedTo" # → Publisher/author
|
||
- "dct:created" # → Document date
|
||
|
||
activity:
|
||
class: "prov:Activity"
|
||
properties:
|
||
- "prov:wasAssociatedWith" # → Extraction agent
|
||
- "prov:used" # → ML model or rules
|
||
- "prov:startedAtTime" # → Extraction timestamp
|
||
|
||
agent:
|
||
class: "prov:Agent"
|
||
examples:
|
||
- "Human curator"
|
||
- "spaCy NER model"
|
||
- "GLAM-NER extraction pipeline"
|
||
|
||
# =============================================================================
|
||
# SOURCE TYPE EXTENSIONS
|
||
# =============================================================================
|
||
#
|
||
# PiCo PersonObservation can be extracted from many source types.
|
||
# Each source type may have specific extraction patterns, but the core
|
||
# PiCo model (observation → name → roles → provenance) remains the same.
|
||
#
|
||
# Source-specific extraction logic belongs in APPLICATION LAYER scripts,
|
||
# not in this convention. This section defines the ABSTRACT patterns.
|
||
# =============================================================================
|
||
|
||
source_type_patterns:
|
||
description: |
|
||
PersonObservation sources fall into categories with different extraction
|
||
patterns. The CH-Annotator handles all source types using the same
|
||
core PiCo model, with source-specific field mappings at extraction time.
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Source Categories
|
||
# ---------------------------------------------------------------------------
|
||
|
||
categories:
|
||
modern_digital:
|
||
description: "Contemporary digital sources with structured data"
|
||
examples:
|
||
- "LinkedIn profiles"
|
||
- "Institutional staff directories"
|
||
- "Academic profile pages"
|
||
- "ORCID records"
|
||
characteristics:
|
||
- "Semi-structured HTML/JSON"
|
||
- "Current/living persons"
|
||
- "Self-reported information"
|
||
- "Timestamped updates"
|
||
typical_properties:
|
||
- "sdo:name"
|
||
- "sdo:jobTitle"
|
||
- "sdo:hasOccupation"
|
||
- "sdo:alumniOf"
|
||
- "sdo:knowsAbout"
|
||
|
||
historical_indices:
|
||
description: "Early modern and historical name indices"
|
||
examples:
|
||
- "Notarial protocol indices"
|
||
- "Church register indices"
|
||
- "Census indices"
|
||
- "Guild membership lists"
|
||
- "Property transfer records"
|
||
characteristics:
|
||
- "Abbreviated names"
|
||
- "Patronymics common"
|
||
- "Latin/vernacular mixing"
|
||
- "Occupation as identifier"
|
||
- "Relational identification ('wife of', 'son of')"
|
||
typical_properties:
|
||
- "pnv:literalName"
|
||
- "pnv:patronym"
|
||
- "picom:hasRole"
|
||
- "crm:P107_has_current_or_former_member"
|
||
- "sdo:spouse"
|
||
- "sdo:parent"
|
||
|
||
archival_descriptions:
|
||
description: "Finding aids, inventories, and archival descriptions"
|
||
examples:
|
||
- "EAD finding aids"
|
||
- "ISAD(G) descriptions"
|
||
- "Collection inventories"
|
||
- "RiC-O records"
|
||
characteristics:
|
||
- "Hierarchical context"
|
||
- "Provenance-focused"
|
||
- "Creator/contributor roles"
|
||
- "Temporal spans"
|
||
typical_properties:
|
||
- "rico:hasCreator"
|
||
- "rico:hasOrHadHolder"
|
||
- "crm:P14_carried_out_by"
|
||
- "crm:P11_had_participant"
|
||
|
||
biographical_dictionaries:
|
||
description: "Structured biographical reference works"
|
||
examples:
|
||
- "Dictionary of National Biography"
|
||
- "KNAW DWDD"
|
||
- "Allgemeines Künstlerlexikon"
|
||
- "Thieme-Becker"
|
||
characteristics:
|
||
- "Standardized entries"
|
||
- "Birth/death dates"
|
||
- "Career summaries"
|
||
- "Cross-references"
|
||
typical_properties:
|
||
- "sdo:birthDate"
|
||
- "sdo:deathDate"
|
||
- "sdo:birthPlace"
|
||
- "sdo:deathPlace"
|
||
- "crm:P98_brought_into_life"
|
||
- "crm:P100_was_death_of"
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Universal Observation Properties (All Source Types)
|
||
# ---------------------------------------------------------------------------
|
||
|
||
universal_properties:
|
||
description: |
|
||
These properties apply to PersonObservation regardless of source type.
|
||
They form the core of the PiCo extraction model.
|
||
|
||
required:
|
||
- property: "picom:hasObservedName"
|
||
description: "The name string as it appears in source"
|
||
range: "pnv:PersonName"
|
||
|
||
- property: "prov:hadPrimarySource"
|
||
description: "The source document/webpage/record"
|
||
range: "prov:Entity"
|
||
|
||
- property: "picom:observedAt"
|
||
description: "When the observation was extracted"
|
||
range: "xsd:dateTime"
|
||
|
||
optional:
|
||
- property: "picom:isObservationOf"
|
||
description: "Links to reconstructed Person entity (if identified)"
|
||
range: "crm:E21_Person"
|
||
|
||
- property: "picom:hasRole"
|
||
description: "Role/position observed with the person"
|
||
range: "org:Role"
|
||
|
||
- property: "picom:observedInContext"
|
||
description: "Surrounding text for disambiguation"
|
||
range: "xsd:string"
|
||
|
||
- property: "picom:confidence"
|
||
description: "Confidence score for extraction"
|
||
range: "xsd:decimal"
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Heritage Relevance Detection (Universal)
|
||
# ---------------------------------------------------------------------------
|
||
|
||
heritage_relevance:
|
||
description: |
|
||
Person observations can be tagged for heritage sector relevance using
|
||
GLAMORCUBESFIXPHDNT type codes. This applies to all source types.
|
||
|
||
type_codes:
|
||
G: "Gallery"
|
||
L: "Library"
|
||
A: "Archive"
|
||
M: "Museum"
|
||
O: "Official institution"
|
||
R: "Research center"
|
||
C: "Corporation"
|
||
U: "Unknown"
|
||
B: "Botanical garden / Zoo"
|
||
E: "Education provider"
|
||
S: "Collecting society"
|
||
F: "Feature / Monument"
|
||
I: "Intangible heritage"
|
||
X: "Mixed types"
|
||
P: "Personal collection"
|
||
H: "Holy site"
|
||
D: "Digital platform"
|
||
N: "NGO"
|
||
T: "Taste/smell heritage"
|
||
|
||
detection_approach: |
|
||
Heritage relevance detection is SOURCE-SPECIFIC and belongs in the
|
||
application layer, not the convention. The convention defines:
|
||
1. The type code vocabulary (GLAMORCUBESFIXPHDNT)
|
||
2. The property for tagging (picom:heritageRelevance)
|
||
3. The expected format (single-letter code + confidence)
|
||
|
||
Application scripts implement source-specific keyword detection,
|
||
organization matching, or ML classification to populate this field.
|
||
|
||
# =============================================================================
|
||
# GLM-4.6 CH-ANNOTATOR INTEGRATION
|
||
# =============================================================================
|
||
#
|
||
# The CH-Annotator can be invoked via GLM-4.6 API for automated extraction.
|
||
# The system prompt is SOURCE-AGNOSTIC and works with any text input.
|
||
# =============================================================================
|
||
|
||
glm_annotator_config:
|
||
model: "glm-4.6"
|
||
api_endpoint: "https://api.z.ai/api/coding/paas/v4/chat/completions"
|
||
temperature: 0.1
|
||
max_tokens: 4000
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Core System Prompt (Source-Agnostic)
|
||
# ---------------------------------------------------------------------------
|
||
|
||
system_prompt: |
|
||
You are a CH-Annotator (Cultural Heritage Annotator) v1.7.0 extraction agent
|
||
with PiCo (Person in Context) ontology integration.
|
||
|
||
## Your Task
|
||
Extract structured person observation data from the provided source text.
|
||
The source may be a modern digital profile, historical index, archival
|
||
description, or any other document containing person references.
|
||
|
||
## Core PiCo Pattern
|
||
Every person mention creates a PersonObservation that is:
|
||
- SOURCE-BOUND: Exact transcription from source, no normalization
|
||
- PROVENANCE-TRACKED: Linked to source document and extraction timestamp
|
||
- RECONSTRUCTION-READY: Can be linked to formal Person entity later
|
||
|
||
## Person Name Vocabulary (PNV)
|
||
Parse names into components (use null for missing parts):
|
||
- literalName: Full name exactly as written in source
|
||
- givenName: First/given name
|
||
- patronym: Patronymic (Janszoon, -dochter, bin, ibn, mac)
|
||
- surnamePrefix: Tussenvoegsel/particle (van, de, von, di, du)
|
||
- baseSurname: Core surname without prefix
|
||
- honorificPrefix: Title before name (Dr., Prof., Heer, Meester)
|
||
- honorificSuffix: Credentials after name (PhD, Jr., III)
|
||
- initials: Initials with periods (e.g., "P.R.", "C.Joh.")
|
||
|
||
## Language-Specific Name Rules
|
||
|
||
### Dutch
|
||
- Tussenvoegsel lowercase after given name: "Jan van Gogh"
|
||
- Capitalized when standalone: "Van Gogh painted..."
|
||
- Common: van, de, van de, van den, van der, 't, 's, op de
|
||
|
||
### Historical/Latin
|
||
- Patronymics: -zoon/-zn, -dochter/-dr, -s (Janszoon, Pietersdochter)
|
||
- Latinized forms: -us, -ius endings (Erasmus Roterodamus)
|
||
- Occupational surnames may be literal (de bakker = the baker)
|
||
|
||
## Role Extraction
|
||
Extract roles/occupations with temporal bounds when available:
|
||
- Role title exactly as stated
|
||
- Associated organization (link to GRP hypernym if institution)
|
||
- Start/end dates or period
|
||
- Heritage relevance code if applicable (GLAMORCUBESFIXPHDNT)
|
||
- Role in source context (from picot_roles thesaurus):
|
||
* child, parent, spouse, witness, declarant, bride, groom, godparent, etc.
|
||
|
||
## Biographical Properties
|
||
Extract when present in source (use null if not stated):
|
||
- birth_date / death_date: ISO format (YYYY, YYYY-MM, or YYYY-MM-DD)
|
||
- birth_place / death_place: Place name as written
|
||
- gender: "Male" or "Female" (only if explicitly stated or inferable)
|
||
- age: Age as stated (e.g., "30", "4 months", "about 25")
|
||
- religion: Religious affiliation if mentioned
|
||
- deceased: true only if death indicated but date unknown
|
||
- address: Physical address as recorded in source
|
||
- floruit: Active period if birth/death unknown
|
||
|
||
## Family Relationship Extraction
|
||
|
||
CRITICAL: For PersonObservations, family relationships MUST refer to OTHER
|
||
persons mentioned in the SAME source document. Cross-source relationships
|
||
belong to PersonReconstructions.
|
||
|
||
### Core Family Relationships
|
||
- parent: A parent of the person (use sdo:parent)
|
||
- children: Children of the person (use sdo:children)
|
||
- spouse: Current spouse (use sdo:spouse)
|
||
- sibling: Brother or sister (use sdo:sibling)
|
||
|
||
### Extended Family
|
||
- grandparent / grandchild
|
||
- uncle_aunt / nephew_niece
|
||
- cousin (symmetric)
|
||
|
||
### Step/Half Relations
|
||
- stepparent / stepchild
|
||
- stepsibling
|
||
- half_sibling (one shared parent)
|
||
|
||
### Ritual/Legal Kinship (common in historical records)
|
||
- godparent / godchild: Baptismal sponsors
|
||
- foster_parent / foster_child
|
||
- legitimized_child: Child recognized through marriage/legal act
|
||
|
||
### In-Law Relations
|
||
- parent_in_law / child_in_law
|
||
- sibling_in_law
|
||
|
||
### Former Partners
|
||
- widow_of: Surviving spouse of deceased (subject is the survivor)
|
||
- previous_partner: Former spouse/partner
|
||
|
||
### Historical Source Patterns
|
||
Common relationship indicators in historical documents (by language):
|
||
|
||
**Dutch**: "huijsvrou van" (wife), "zoon van" (son of), "weduwe van" (widow),
|
||
"peter/meter" (godfather/godmother), "getuige" (witness)
|
||
|
||
**Latin**: "filius/filia" (son/daughter), "uxor" (wife), "vidua" (widow),
|
||
"quondam" (the late)
|
||
|
||
**German**: "Ehefrau von" (wife), "Sohn/Tochter von" (son/daughter of),
|
||
"Witwe von" (widow of)
|
||
|
||
**Arabic** (نسب - patronymic): "ابن/بن" (ibn/bin - son of), "بنت" (bint - daughter of),
|
||
"زوج/زوجة" (zawj/zawja - husband/wife), "أرملة" (armala - widow),
|
||
"المرحوم" (al-marhum - the late), "آل" (Al - family of)
|
||
|
||
**Ottoman Turkish**: "oğlu" (son of), "kızı" (daughter of), "zevcesi" (wife),
|
||
"merhum/merhume" (the late)
|
||
|
||
**French**: "fils/fille de" (son/daughter of), "épouse de" (wife of),
|
||
"veuve de" (widow of), "feu/feue" (the late)
|
||
|
||
**Hebrew**: "בן/בת" (ben/bat - son/daughter of), "אשת" (eshet - wife of),
|
||
"אלמנה" (almana - widow), "ז״ל" (z"l - of blessed memory)
|
||
|
||
**Persian/Farsi**: "پسر/دختر" (pesar/dokhtar - son/daughter), "زن" (zan - wife),
|
||
"بیوه" (biveh - widow), "مرحوم" (marhum - the late)
|
||
|
||
**Spanish**: "hijo/hija de" (son/daughter of), "esposa de" (wife of),
|
||
"viuda de" (widow of), "padrino/madrina" (godfather/godmother)
|
||
|
||
**Portuguese**: "filho/filha de" (son/daughter of), "esposa de" (wife of),
|
||
"viúva de" (widow of), "padrinho/madrinha" (godfather/godmother)
|
||
|
||
For comprehensive patterns (10 languages): modules/relationships/family.yaml
|
||
|
||
## Source Types (for source_type field)
|
||
Use appropriate category:
|
||
- modern_digital: LinkedIn, staff directories, ORCID
|
||
- historical_indices: Notarial protocols, guild lists
|
||
- civil_registration: Birth/marriage/death certificates
|
||
- church_records: Baptism, marriage, burial registers
|
||
- archival_descriptions: Finding aids, inventories
|
||
- biographical_dictionaries: DNB, AKL, reference works
|
||
- census: Population census records
|
||
|
||
## Output Format
|
||
Return ONLY valid JSON (no markdown, no explanation):
|
||
|
||
{
|
||
"pico_observation": {
|
||
"observation_id": "<source-derived-id>",
|
||
"observed_at": "<extraction-timestamp>",
|
||
"source_type": "<source_category>",
|
||
"source_reference": "<source-identifier>"
|
||
},
|
||
"persons": [
|
||
{
|
||
"person_index": 0,
|
||
"pnv_name": {
|
||
"literalName": "Name as written",
|
||
"givenName": null,
|
||
"patronym": null,
|
||
"surnamePrefix": null,
|
||
"baseSurname": null,
|
||
"honorificPrefix": null,
|
||
"honorificSuffix": null,
|
||
"initials": null
|
||
},
|
||
"roles": [
|
||
{
|
||
"role_title": "Role as stated",
|
||
"role_in_source": "child|declarant|witness|bride|groom|null",
|
||
"organization": "Org name if mentioned",
|
||
"period": "Temporal info if available",
|
||
"heritage_relevant": false,
|
||
"heritage_type": null
|
||
}
|
||
],
|
||
"biographical": {
|
||
"birth_date": null,
|
||
"death_date": null,
|
||
"birth_place": null,
|
||
"death_place": null,
|
||
"gender": null,
|
||
"age": null,
|
||
"religion": null,
|
||
"deceased": null,
|
||
"address": null,
|
||
"floruit": null
|
||
},
|
||
"family_relationships": {
|
||
"parent": [],
|
||
"children": [],
|
||
"spouse": [],
|
||
"sibling": [],
|
||
"grandparent": [],
|
||
"grandchild": [],
|
||
"uncle_aunt": [],
|
||
"nephew_niece": [],
|
||
"cousin": [],
|
||
"stepparent": [],
|
||
"stepchild": [],
|
||
"stepsibling": [],
|
||
"half_sibling": [],
|
||
"foster_parent": [],
|
||
"foster_child": [],
|
||
"godparent": [],
|
||
"godchild": [],
|
||
"parent_in_law": [],
|
||
"child_in_law": [],
|
||
"sibling_in_law": [],
|
||
"previous_partner": [],
|
||
"widow_of": null
|
||
},
|
||
"context": "Surrounding text for disambiguation"
|
||
}
|
||
],
|
||
"organizations_mentioned": [
|
||
{
|
||
"name": "Organization name",
|
||
"type": "Heritage type code or null",
|
||
"role_in_source": "employer|creator|publisher|etc"
|
||
}
|
||
],
|
||
"temporal_references": [
|
||
{
|
||
"expression": "Date/period as written",
|
||
"normalized": "ISO date if parseable",
|
||
"type": "DATE|DURATION|SET"
|
||
}
|
||
],
|
||
"locations_mentioned": [
|
||
{
|
||
"name": "Place name as written",
|
||
"type": "city|region|country|address"
|
||
}
|
||
]
|
||
}
|
||
|
||
## Relationship Reference Format
|
||
Family relationship arrays contain references to other persons in same source:
|
||
- Use person_index (integer) to reference persons array position
|
||
- Include target_name for readability
|
||
|
||
Example for a marriage record:
|
||
```json
|
||
{
|
||
"person_index": 0,
|
||
"pnv_name": {"literalName": "Jan Pietersz"},
|
||
"family_relationships": {
|
||
"spouse": [{"person_index": 1, "target_name": "Maria Jansdr"}],
|
||
"parent": [{"person_index": 2, "target_name": "Pieter Jansz"}]
|
||
}
|
||
}
|
||
```
|
||
|
||
## Critical Rules
|
||
1. ONLY extract data that EXISTS in the source. NEVER fabricate.
|
||
2. Use null for missing fields, [] for empty arrays.
|
||
3. Preserve original spelling/language from source.
|
||
4. heritage_type must be single-letter GLAMORCUBESFIXPHDNT code.
|
||
5. For historical sources, preserve archaic spellings exactly.
|
||
6. Extract ALL persons mentioned, not just the primary subject.
|
||
7. Family relationships MUST reference persons in SAME source only.
|
||
8. Use person_index for relationship references (0-based array index).
|
||
9. Gender: only "Male"/"Female"/null - never infer without evidence.
|
||
10. Age: preserve as stated, include qualifier ("about 25", "4 months").
|
||
11. For role_in_source, use picot_roles terms when applicable.
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# LinkedIn Profile System Prompt (Modern Digital Sources) - COMPACT VERSION
|
||
# ---------------------------------------------------------------------------
|
||
# This prompt is optimized for GLM-4.6 context window. The original verbose
|
||
# version caused empty responses. This compact version maintains all essential
|
||
# extraction logic while staying under 2KB.
|
||
# ---------------------------------------------------------------------------
|
||
|
||
linkedin_system_prompt: |
|
||
You are a LinkedIn Profile Annotator for heritage sector analysis.
|
||
|
||
## Task
|
||
Extract structured career data from LinkedIn profile markdown into JSON.
|
||
|
||
## Output JSON Structure
|
||
{
|
||
"pico_observation": {
|
||
"observation_id": "linkedin-[slug]-[date]",
|
||
"source_type": "modern_digital",
|
||
"source_reference": "[LinkedIn URL]"
|
||
},
|
||
"persons": [{
|
||
"pnv_name": {"literalName": "...", "givenName": "...", "surnamePrefix": "van/de or null", "baseSurname": "..."},
|
||
"headline": "...",
|
||
"location": "...",
|
||
"connections": "...",
|
||
"about": "...",
|
||
"profile_image_url": "LinkedIn CDN URL or null",
|
||
"heritage_relevant_experience": [{
|
||
"role": "Job Title",
|
||
"organization": {
|
||
"name": "Org",
|
||
"linkedin_url": "https://linkedin.com/company/...",
|
||
"heritage_type": "M|A|L|R|G|E|D|O|B|H|F|S|C or null",
|
||
"industry": "...",
|
||
"size": "...",
|
||
"founded": "...",
|
||
"ownership": "Nonprofit|Public|Private"
|
||
},
|
||
"time_period": {"start": "YYYY-MM", "end": "YYYY-MM or null", "is_current": true/false, "duration": "..."},
|
||
"location": {"city": "...", "region": "...", "country": "..."},
|
||
"department": "...",
|
||
"level": "...",
|
||
"description": "..."
|
||
}],
|
||
"other_experience": [],
|
||
"education": [{"institution": "...", "linkedin_url": "...", "degree": "...", "field": "...", "time_period": {"start": "YYYY", "end": "YYYY"}}],
|
||
"skills": [],
|
||
"languages": [{"language": "...", "proficiency": "..."}]
|
||
}],
|
||
"organizations_mentioned": [{"name": "...", "linkedin_url": "...", "heritage_type": "...", "industry": "...", "size": "...", "founded": "...", "ownership": "...", "role_in_source": "employer|education"}]
|
||
}
|
||
|
||
## Heritage Type Codes
|
||
M=Museum, A=Archive, L=Library, R=Research, G=Gallery, E=Education, D=Digital, O=Official, B=Botanical/Zoo, H=Holy site, F=Feature, S=Society, C=Corporation, null=Non-heritage
|
||
|
||
## Extraction Rules
|
||
1. Parse [Text](url) markdown links - extract BOTH text AND url
|
||
2. Company metadata appears after "Company:" - parse all fields (size, founded, ownership, industry)
|
||
3. Only heritage_relevant_experience if org is GLAM-related (museums, archives, libraries, research institutes, galleries, etc.)
|
||
4. other_experience for non-heritage orgs (retail, finance, tech, etc.)
|
||
5. For Dutch names: van, de, van der, van den → surnamePrefix
|
||
6. Date parsing: "Jan 2022" → "2022-01", "Present" → end: null + is_current: true
|
||
7. Copy duration string exactly: "3 years and 10 months"
|
||
8. NEVER fabricate data - use null for missing fields
|
||
9. Return ONLY valid JSON, no markdown code blocks, no explanation
|
||
|
||
# =============================================================================
|
||
# PERSON RECONSTRUCTION PATTERN
|
||
# =============================================================================
|
||
#
|
||
# PersonReconstruction is a reconstructed person entity derived from one or
|
||
# more PersonObservations. It represents the scholarly consensus about a
|
||
# historical person based on available evidence.
|
||
# =============================================================================
|
||
|
||
person_reconstruction_pattern:
|
||
description: |
|
||
A PersonReconstruction is created by linking one or more PersonObservations
|
||
to form a unified person entity. This is the scholarly interpretation layer
|
||
that connects source-bound observations to a conceptual person.
|
||
|
||
Key distinction:
|
||
- PersonObservation: What is OBSERVED in a specific source (exact transcription)
|
||
- PersonReconstruction: What is INFERRED about the person (normalized, linked)
|
||
|
||
A single PersonReconstruction may derive from observations across:
|
||
- Multiple sources (birth record + marriage record + death record)
|
||
- Different time periods (mentions across decades)
|
||
- Various name forms ("Jan Jansz" + "Johannes Jansen" + "J. Jansen")
|
||
|
||
class: "pico:PersonReconstruction"
|
||
class_uri: "https://personsincontext.org/model#PersonReconstruction"
|
||
superclass: "pico:Person"
|
||
|
||
required_properties:
|
||
- property: "prov:wasDerivedFrom"
|
||
description: "Links to source PersonObservation(s)"
|
||
range: "pico:PersonObservation"
|
||
cardinality: "1..*"
|
||
note: "Every reconstruction MUST link to at least one observation"
|
||
|
||
- property: "prov:wasGeneratedBy"
|
||
description: "Links to the reconstruction Activity"
|
||
range: "prov:Activity"
|
||
cardinality: "1"
|
||
note: "Documents how/when/by whom reconstruction was created"
|
||
|
||
optional_properties:
|
||
- property: "prov:wasRevisionOf"
|
||
description: "Links to previous version of this reconstruction"
|
||
range: "pico:PersonReconstruction"
|
||
cardinality: "0..1"
|
||
note: "For tracking updates to reconstructions over time"
|
||
|
||
- property: "sdo:name"
|
||
description: "Normalized/preferred name form"
|
||
range: "xsd:string"
|
||
note: "The canonical name for this person"
|
||
|
||
- property: "sdo:additionalName"
|
||
description: "Structured name following PNV"
|
||
range: "pnv:PersonName"
|
||
note: "Full name breakdown using Person Name Vocabulary"
|
||
|
||
- property: "sdo:givenName"
|
||
description: "Given/first name"
|
||
range: "xsd:string"
|
||
|
||
- property: "sdo:familyName"
|
||
description: "Family/surname"
|
||
range: "xsd:string"
|
||
|
||
- property: "sdo:gender"
|
||
description: "Gender of the person"
|
||
range: "sdo:GenderType"
|
||
values: ["sdo:Male", "sdo:Female"]
|
||
|
||
- property: "sdo:birthDate"
|
||
description: "Birth date (ISO 8601)"
|
||
range: "xsd:date"
|
||
note: "May be incomplete: YYYY, YYYY-MM, or YYYY-MM-DD"
|
||
|
||
- property: "sdo:birthPlace"
|
||
description: "Place of birth"
|
||
range: "xsd:string or xsd:anyURI"
|
||
note: "Prefer linking to GeoNames or Wikidata"
|
||
|
||
- property: "sdo:deathDate"
|
||
description: "Death date (ISO 8601)"
|
||
range: "xsd:date"
|
||
|
||
- property: "sdo:deathPlace"
|
||
description: "Place of death"
|
||
range: "xsd:string or xsd:anyURI"
|
||
|
||
example:
|
||
description: "PersonReconstruction derived from multiple observations"
|
||
turtle: |
|
||
cbg:person_reconstruction_anna_koppen
|
||
a pico:PersonReconstruction ;
|
||
sdo:name "Anna Maria Koppen" ;
|
||
sdo:familyName "Koppen" ;
|
||
sdo:givenName "Anna Maria" ;
|
||
sdo:gender sdo:Female ;
|
||
sdo:birthPlace "Haarlem" ;
|
||
sdo:birthDate "1860-03-31"^^xsd:date ;
|
||
sdo:deathPlace "Detroit, USA" ;
|
||
sdo:deathDate "1926"^^xsd:gYear ;
|
||
prov:wasDerivedFrom nha:marriage_1885_po_1 ,
|
||
cbg:emigration_1887_po_1 ,
|
||
us:death_1926_po_1 ;
|
||
prov:wasGeneratedBy cbg:reconstruction_activity_01 .
|
||
|
||
# =============================================================================
|
||
# SOURCE AND SCAN CLASSES
|
||
# =============================================================================
|
||
#
|
||
# Sources (sdo:ArchiveComponent) and Scans (sdo:ImageObject) document where
|
||
# PersonObservations were extracted from. Essential for provenance.
|
||
# =============================================================================
|
||
|
||
source_classes:
|
||
|
||
archive_component:
|
||
description: |
|
||
A Source document from which PersonObservations are extracted.
|
||
PiCo does not aim to fully describe archival sources (use RiC-O or DC for that),
|
||
but requires minimal identification for provenance tracking.
|
||
|
||
class: "sdo:ArchiveComponent"
|
||
class_uri: "https://schema.org/ArchiveComponent"
|
||
superclass: "sdo:CreativeWork"
|
||
|
||
properties:
|
||
- property: "sdo:name"
|
||
description: "Identifying name for the source"
|
||
range: "xsd:string"
|
||
cardinality: "1"
|
||
note: "Combine title, date, archive location for identification"
|
||
example: "BS Marriage Haarlem, November 11, 1885, certificate number 321"
|
||
|
||
- property: "sdo:additionalType"
|
||
description: "Type of source document"
|
||
range: "picot_sourcetypes:Concept"
|
||
note: "Use PiCo SourceType thesaurus"
|
||
|
||
- property: "sdo:dateCreated"
|
||
description: "Date the source was created"
|
||
range: "xsd:date"
|
||
|
||
- property: "sdo:holdingArchive"
|
||
description: "Institution holding the source"
|
||
range: "xsd:anyURI"
|
||
note: "Link to heritage custodian (GHCID or Wikidata)"
|
||
|
||
- property: "sdo:url"
|
||
description: "Permalink to the source"
|
||
range: "sdo:URL"
|
||
note: "Preferably a persistent identifier"
|
||
|
||
- property: "sdo:contentLocation"
|
||
description: "Geographic coverage of the source"
|
||
range: "xsd:string or xsd:anyURI"
|
||
|
||
- property: "sdo:associatedMedia"
|
||
description: "Link to scan(s) of the source"
|
||
range: "sdo:ImageObject"
|
||
cardinality: "0..*"
|
||
|
||
image_object:
|
||
description: |
|
||
A Scan of a source document. Links to the digital image at the holding archive.
|
||
|
||
class: "sdo:ImageObject"
|
||
class_uri: "https://schema.org/ImageObject"
|
||
superclass: "sdo:CreativeWork"
|
||
|
||
properties:
|
||
- property: "sdo:url"
|
||
description: "URL to the full scan"
|
||
range: "sdo:URL"
|
||
note: "Preferably IIIF manifest"
|
||
|
||
- property: "sdo:thumbnail"
|
||
description: "URL to thumbnail image"
|
||
range: "sdo:ImageObject"
|
||
|
||
- property: "sdo:embedUrl"
|
||
description: "URL to image viewer"
|
||
range: "sdo:URL"
|
||
|
||
- property: "sdo:position"
|
||
description: "Position in sequence of scans"
|
||
range: "xsd:int"
|
||
note: "For multi-page sources"
|
||
|
||
# =============================================================================
|
||
# BIOGRAPHICAL PROPERTIES
|
||
# =============================================================================
|
||
#
|
||
# Properties for capturing biographical details about persons in observations.
|
||
# These appear in the source and are transcribed to the observation.
|
||
# =============================================================================
|
||
|
||
biographical_properties:
|
||
description: |
|
||
Biographical properties capture personal details as they appear in sources.
|
||
These are used for both PersonObservation (source-bound) and
|
||
PersonReconstruction (normalized).
|
||
|
||
age:
|
||
property: "pico:hasAge"
|
||
property_uri: "https://personsincontext.org/model#hasAge"
|
||
description: "Age of person as stated in source"
|
||
range: "xsd:string"
|
||
domain: "pico:PersonObservation"
|
||
note: |
|
||
Used when birth date unknown but age is recorded.
|
||
Age assumed in years unless specified ("4" = 4 years, "4 months" = 4 months).
|
||
Numerical preferred over text ("4" not "four").
|
||
examples:
|
||
- "30"
|
||
- "4 months"
|
||
- "about 25"
|
||
|
||
religion:
|
||
property: "pico:hasReligion"
|
||
property_uri: "https://personsincontext.org/model#hasReligion"
|
||
description: "Religious affiliation as stated in source"
|
||
range: "xsd:string or xsd:anyURI"
|
||
domain: "pico:Person"
|
||
note: "Can link to SKOS thesaurus for religions"
|
||
examples:
|
||
- "Catholic"
|
||
- "Reformed"
|
||
- "Jewish"
|
||
|
||
deceased:
|
||
property: "pico:deceased"
|
||
property_uri: "https://personsincontext.org/model#deceased"
|
||
description: "Indication that person is deceased (when death date unknown)"
|
||
range: "xsd:boolean"
|
||
domain: "pico:PersonObservation"
|
||
note: |
|
||
Only used when deathDate is unknown but death is indicated.
|
||
A person without deathDate and without deceased:true is assumed alive.
|
||
Important for privacy considerations in publishing person records.
|
||
|
||
gender:
|
||
property: "sdo:gender"
|
||
property_uri: "https://schema.org/gender"
|
||
description: "Gender of the person"
|
||
range: "sdo:GenderType"
|
||
domain: "pico:Person"
|
||
values:
|
||
- uri: "sdo:Male"
|
||
label: "Male"
|
||
- uri: "sdo:Female"
|
||
label: "Female"
|
||
|
||
address:
|
||
property: "sdo:address"
|
||
property_uri: "https://schema.org/address"
|
||
description: "Physical address as mentioned in source"
|
||
range: "xsd:string"
|
||
domain: "pico:PersonObservation"
|
||
note: "Address exactly as recorded in source"
|
||
|
||
initials:
|
||
property: "pnv:initials"
|
||
property_uri: "https://w3id.org/pnv#initials"
|
||
description: "Initials of given name(s)"
|
||
range: "xsd:string"
|
||
domain: "pnv:PersonName"
|
||
note: "Each initial followed by period (e.g., 'P.R.', 'H.A.F.M.O.')"
|
||
examples:
|
||
- "P.R."
|
||
- "C.Joh."
|
||
- "H.A.F.M.O."
|
||
|
||
# =============================================================================
|
||
# FAMILY RELATIONSHIP PROPERTIES
|
||
# =============================================================================
|
||
#
|
||
# PiCo defines extensive family relationship properties for genealogical data.
|
||
# These enable modeling complex family structures from historical records.
|
||
# =============================================================================
|
||
|
||
family_relationships:
|
||
description: |
|
||
Family relationship properties link persons within and across sources.
|
||
|
||
Rules:
|
||
- For PersonObservations: relationships refer to OTHER observations on SAME source
|
||
- For PersonReconstructions: relationships refer to other reconstructions
|
||
|
||
Property characteristics:
|
||
- Symmetric: If A hasRelation B, then B hasRelation A (spouses, siblings, cousins)
|
||
- Transitive: hasAncestor/hasDescendant chain through generations
|
||
- Inverse pairs: parent/children, grandparent/grandchild, etc.
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Core Family (Schema.org)
|
||
# ---------------------------------------------------------------------------
|
||
|
||
core_relationships:
|
||
- property: "sdo:parent"
|
||
property_uri: "https://schema.org/parent"
|
||
description: "A parent of the person"
|
||
inverse: "sdo:children"
|
||
subPropertyOf: ["sdo:relatedTo", "pico:hasAncestor"]
|
||
note: "Biological or legal parent"
|
||
|
||
- property: "sdo:children"
|
||
property_uri: "https://schema.org/children"
|
||
description: "A child of the person"
|
||
inverse: "sdo:parent"
|
||
subPropertyOf: ["sdo:relatedTo", "pico:hasDescendant"]
|
||
|
||
- property: "sdo:spouse"
|
||
property_uri: "https://schema.org/spouse"
|
||
description: "The person's spouse"
|
||
symmetric: true
|
||
subPropertyOf: "sdo:relatedTo"
|
||
|
||
- property: "sdo:sibling"
|
||
property_uri: "https://schema.org/sibling"
|
||
description: "A brother or sister"
|
||
symmetric: true
|
||
subPropertyOf: "sdo:relatedTo"
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Transitive Ancestry (PiCo)
|
||
# ---------------------------------------------------------------------------
|
||
|
||
ancestry_relationships:
|
||
- property: "pico:hasAncestor"
|
||
property_uri: "https://personsincontext.org/model#hasAncestor"
|
||
description: "Any ancestor (parent, grandparent, etc.)"
|
||
type: "owl:TransitiveProperty"
|
||
inverse: "pico:hasDescendant"
|
||
note: "Not used directly; parent→parent chains automatically create ancestors"
|
||
|
||
- property: "pico:hasDescendant"
|
||
property_uri: "https://personsincontext.org/model#hasDescendant"
|
||
description: "Any descendant (child, grandchild, etc.)"
|
||
type: "owl:TransitiveProperty"
|
||
inverse: "pico:hasAncestor"
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Grandparents/Grandchildren
|
||
# ---------------------------------------------------------------------------
|
||
|
||
grandparent_relationships:
|
||
- property: "pico:hasGrandparent"
|
||
property_uri: "https://personsincontext.org/model#hasGrandparent"
|
||
inverse: "pico:hasGrandchild"
|
||
|
||
- property: "pico:hasGrandchild"
|
||
property_uri: "https://personsincontext.org/model#hasGrandchild"
|
||
inverse: "pico:hasGrandparent"
|
||
|
||
- property: "pico:hasGreat-grandparent"
|
||
property_uri: "https://personsincontext.org/model#hasGreat-grandparent"
|
||
inverse: "pico:hasGreat-grandchild"
|
||
|
||
- property: "pico:hasGreat-grandchild"
|
||
property_uri: "https://personsincontext.org/model#hasGreat-grandchild"
|
||
inverse: "pico:hasGreat-grandparent"
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Aunts/Uncles and Nieces/Nephews
|
||
# ---------------------------------------------------------------------------
|
||
|
||
extended_family:
|
||
- property: "pico:hasUncle_Aunt"
|
||
property_uri: "https://personsincontext.org/model#hasUncle_Aunt"
|
||
description: "An uncle or aunt (sibling of parent)"
|
||
inverse: "pico:hasNephew_Niece"
|
||
|
||
- property: "pico:hasNephew_Niece"
|
||
property_uri: "https://personsincontext.org/model#hasNephew_Niece"
|
||
description: "A nephew or niece (child of sibling)"
|
||
inverse: "pico:hasUncle_Aunt"
|
||
|
||
- property: "pico:hasCousin"
|
||
property_uri: "https://personsincontext.org/model#hasCousin"
|
||
description: "A cousin (child of parent's sibling)"
|
||
symmetric: true
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Step-family
|
||
# ---------------------------------------------------------------------------
|
||
|
||
step_relationships:
|
||
- property: "pico:hasStepparent"
|
||
property_uri: "https://personsincontext.org/model#hasStepparent"
|
||
description: "A stepparent (spouse of biological parent)"
|
||
inverse: "pico:hasStepchild"
|
||
|
||
- property: "pico:hasStepchild"
|
||
property_uri: "https://personsincontext.org/model#hasStepchild"
|
||
inverse: "pico:hasStepparent"
|
||
|
||
- property: "pico:hasStepsibling"
|
||
property_uri: "https://personsincontext.org/model#hasStepsibling"
|
||
description: "A stepbrother or stepsister"
|
||
symmetric: true
|
||
|
||
- property: "pico:hasHalf-sibling"
|
||
property_uri: "https://personsincontext.org/model#hasHalf-sibling"
|
||
description: "A half-brother or half-sister (one shared parent)"
|
||
symmetric: true
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Foster/Godparent
|
||
# ---------------------------------------------------------------------------
|
||
|
||
non_biological_relationships:
|
||
- property: "pico:hasFosterParent"
|
||
property_uri: "https://personsincontext.org/model#hasFosterParent"
|
||
inverse: "pico:hasFosterChild"
|
||
|
||
- property: "pico:hasFosterChild"
|
||
property_uri: "https://personsincontext.org/model#hasFosterChild"
|
||
inverse: "pico:hasFosterParent"
|
||
|
||
- property: "pico:hasGodparent"
|
||
property_uri: "https://personsincontext.org/model#hasGodparent"
|
||
description: "A godparent (witness at baptism)"
|
||
inverse: "pico:hasGodchild"
|
||
|
||
- property: "pico:hasGodchild"
|
||
property_uri: "https://personsincontext.org/model#hasGodchild"
|
||
inverse: "pico:hasGodparent"
|
||
|
||
- property: "pico:hasLegitimizedChild"
|
||
property_uri: "https://personsincontext.org/model#hasLegitimizedChild"
|
||
description: "A child legitimized by marriage or legal recognition"
|
||
inverse: "pico:isLegitimitezedChildOf"
|
||
|
||
- property: "pico:isLegitimitezedChildOf"
|
||
property_uri: "https://personsincontext.org/model#isLegitimitezedChildOf"
|
||
inverse: "pico:hasLegitimizedChild"
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# In-Laws
|
||
# ---------------------------------------------------------------------------
|
||
|
||
in_law_relationships:
|
||
- property: "pico:hasParent-in-law"
|
||
property_uri: "https://personsincontext.org/model#hasParent-in-law"
|
||
inverse: "pico:hasChild-in-law"
|
||
|
||
- property: "pico:hasChild-in-law"
|
||
property_uri: "https://personsincontext.org/model#hasChild-in-law"
|
||
inverse: "pico:hasParent-in-law"
|
||
|
||
- property: "pico:hasSibling-in-law"
|
||
property_uri: "https://personsincontext.org/model#hasSibling-in-law"
|
||
description: "Brother/sister-in-law"
|
||
symmetric: true
|
||
|
||
- property: "pico:hasGrandparent-in-law"
|
||
property_uri: "https://personsincontext.org/model#hasGrandparent-in-law"
|
||
inverse: "pico:hasGrandchild-in-law"
|
||
|
||
- property: "pico:hasGrandchild-in-law"
|
||
property_uri: "https://personsincontext.org/model#hasGrandchild-in-law"
|
||
inverse: "pico:hasGrandparent-in-law"
|
||
|
||
- property: "pico:hasUncle_Aunt-in-law"
|
||
property_uri: "https://personsincontext.org/model#hasUncle_Aunt-in-law"
|
||
inverse: "pico:hasNephew_Niece-in-law"
|
||
|
||
- property: "pico:hasNephew_Niece-in-law"
|
||
property_uri: "https://personsincontext.org/model#hasNephew_Niece-in-law"
|
||
inverse: "pico:hasUncle_Aunt-in-law"
|
||
|
||
- property: "pico:hasCousin-in-law"
|
||
property_uri: "https://personsincontext.org/model#hasCousin-in-law"
|
||
symmetric: true
|
||
|
||
- property: "pico:hasStepparent-in-law"
|
||
property_uri: "https://personsincontext.org/model#hasStepparent-in-law"
|
||
inverse: "pico:hasStepchild-in-law"
|
||
|
||
- property: "pico:hasStepchild-in-law"
|
||
property_uri: "https://personsincontext.org/model#hasStepchild-in-law"
|
||
inverse: "pico:hasStepparent-in-law"
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Former Partners
|
||
# ---------------------------------------------------------------------------
|
||
|
||
former_partner_relationships:
|
||
- property: "pico:isWidOf"
|
||
property_uri: "https://personsincontext.org/model#isWidOf"
|
||
description: "Is widow/widower of deceased spouse"
|
||
note: "The subject is the surviving partner"
|
||
|
||
- property: "pico:hasPreviousPartner"
|
||
property_uri: "https://personsincontext.org/model#hasPreviousPartner"
|
||
description: "A former spouse or partner"
|
||
symmetric: true
|
||
|
||
# =============================================================================
|
||
# PROVENANCE MODEL (PROV-O INTEGRATION)
|
||
# =============================================================================
|
||
#
|
||
# Enhanced provenance model for tracking observation extraction and
|
||
# reconstruction creation activities.
|
||
# =============================================================================
|
||
|
||
enhanced_provenance_model:
|
||
description: |
|
||
PiCo uses W3C PROV-O for provenance tracking at two levels:
|
||
|
||
1. OBSERVATION LEVEL: Where did this observation come from?
|
||
- prov:hadPrimarySource → Source document
|
||
- prov:wasGeneratedBy → Extraction activity (optional)
|
||
|
||
2. RECONSTRUCTION LEVEL: How was this person entity created?
|
||
- prov:wasDerivedFrom → Source observation(s)
|
||
- prov:wasGeneratedBy → Reconstruction activity
|
||
- prov:wasRevisionOf → Previous reconstruction version
|
||
|
||
activity_class:
|
||
class: "prov:Activity"
|
||
class_uri: "http://www.w3.org/ns/prov#Activity"
|
||
description: "The activity that generated a PersonReconstruction"
|
||
|
||
properties:
|
||
- property: "prov:wasAssociatedWith"
|
||
description: "Agent responsible for the activity"
|
||
range: "prov:Agent"
|
||
|
||
- property: "prov:startedAtTime"
|
||
description: "When the activity started"
|
||
range: "xsd:dateTime"
|
||
|
||
- property: "prov:endedAtTime"
|
||
description: "When the activity completed"
|
||
range: "xsd:dateTime"
|
||
|
||
- property: "prov:used"
|
||
description: "Resources/tools used in the activity"
|
||
range: "prov:Entity"
|
||
note: "E.g., ML model, matching algorithm, rule set"
|
||
|
||
types:
|
||
human_reconstruction:
|
||
description: "Manual reconstruction by researcher"
|
||
note: "Provide: time, place, knowledge sources, researcher name"
|
||
|
||
algorithmic_reconstruction:
|
||
description: "Automated reconstruction by software"
|
||
note: "Provide: algorithm name, version, configuration, parameters"
|
||
|
||
agent_class:
|
||
class: "prov:Agent"
|
||
class_uri: "http://www.w3.org/ns/prov#Agent"
|
||
description: "Person or organization responsible for reconstruction"
|
||
|
||
properties:
|
||
- property: "sdo:name"
|
||
description: "Name of the agent"
|
||
range: "xsd:string"
|
||
|
||
- property: "sdo:url"
|
||
description: "URL identifying the agent"
|
||
range: "sdo:URL"
|
||
|
||
examples:
|
||
- name: "CBG|Center for Family History"
|
||
url: "https://cbg.nl"
|
||
type: "organization"
|
||
|
||
- name: "GLM-4.6 Person Extractor v1.0"
|
||
url: null
|
||
type: "software"
|
||
|
||
derivation_properties:
|
||
- property: "prov:wasDerivedFrom"
|
||
property_uri: "http://www.w3.org/ns/prov#wasDerivedFrom"
|
||
description: "Links PersonReconstruction to source PersonObservation(s)"
|
||
domain: "pico:PersonReconstruction"
|
||
range: "pico:PersonObservation"
|
||
cardinality: "1..*"
|
||
note: "REQUIRED for all PersonReconstructions"
|
||
|
||
- property: "prov:wasRevisionOf"
|
||
property_uri: "http://www.w3.org/ns/prov#wasRevisionOf"
|
||
description: "Links to previous version of reconstruction"
|
||
domain: "pico:PersonReconstruction"
|
||
range: "pico:PersonReconstruction"
|
||
cardinality: "0..1"
|
||
note: "For tracking reconstruction updates over time"
|
||
|
||
# =============================================================================
|
||
# PICO VOCABULARIES/THESAURI
|
||
# =============================================================================
|
||
#
|
||
# PiCo provides controlled vocabularies for roles, source types, and events.
|
||
# =============================================================================
|
||
|
||
pico_vocabularies:
|
||
description: |
|
||
PiCo defines three SKOS concept schemes for controlled terminology:
|
||
|
||
- Roles: The role a person plays in a source (child, declarant, witness, etc.)
|
||
- SourceTypes: Types of historical sources (birth certificate, census, etc.)
|
||
- EventTypes: Types of life events (birth, marriage, death, etc.)
|
||
|
||
roles_thesaurus:
|
||
id: "picot_roles"
|
||
uri: "https://terms.personsincontext.org/roles/"
|
||
type: "skos:ConceptScheme"
|
||
label: "Persons in Context role thesaurus"
|
||
description: "Roles that persons can have in historical sources"
|
||
usage: |
|
||
Use pico:hasRole property with a term from this thesaurus.
|
||
Example: picot_roles:575 (child), picot_roles:489 (declarant)
|
||
example_concepts:
|
||
- id: "575"
|
||
label: "child"
|
||
description: "Person appearing as child in a record"
|
||
|
||
- id: "489"
|
||
label: "declarant"
|
||
description: "Person declaring/reporting an event"
|
||
|
||
- id: "witness"
|
||
label: "witness"
|
||
description: "Person witnessing an event or signing a document"
|
||
|
||
- id: "bride"
|
||
label: "bride"
|
||
description: "Female partner in a marriage"
|
||
|
||
- id: "groom"
|
||
label: "groom"
|
||
description: "Male partner in a marriage"
|
||
|
||
sourcetypes_thesaurus:
|
||
id: "picot_sourcetypes"
|
||
uri: "https://terms.personsincontext.org/sourcetypes/"
|
||
type: "skos:ConceptScheme"
|
||
label: "Persons in Context sourceType thesaurus"
|
||
description: "Types of historical sources containing person observations"
|
||
usage: |
|
||
Use sdo:additionalType property on sdo:ArchiveComponent.
|
||
Example: picot_sourcetypes:551 (civil registry: birth)
|
||
example_concepts:
|
||
- id: "551"
|
||
label: "civil registry: birth"
|
||
description: "Birth certificate from civil registration"
|
||
|
||
- id: "marriage"
|
||
label: "civil registry: marriage"
|
||
description: "Marriage certificate"
|
||
|
||
- id: "death"
|
||
label: "civil registry: death"
|
||
description: "Death certificate"
|
||
|
||
- id: "census"
|
||
label: "census"
|
||
description: "Population census record"
|
||
|
||
- id: "church_baptism"
|
||
label: "church record: baptism"
|
||
description: "Baptismal record from church register"
|
||
|
||
- id: "notarial"
|
||
label: "notarial record"
|
||
description: "Notarial act or protocol"
|
||
|
||
eventtypes_thesaurus:
|
||
id: "picot_eventtypes"
|
||
uri: "https://terms.personsincontext.org/eventtypes/"
|
||
type: "skos:ConceptScheme"
|
||
label: "Persons in Context eventType thesaurus"
|
||
description: "Types of life events documented in sources"
|
||
example_concepts:
|
||
- id: "birth"
|
||
label: "birth"
|
||
|
||
- id: "baptism"
|
||
label: "baptism"
|
||
|
||
- id: "marriage"
|
||
label: "marriage"
|
||
|
||
- id: "death"
|
||
label: "death"
|
||
|
||
- id: "burial"
|
||
label: "burial"
|
||
|
||
- id: "emigration"
|
||
label: "emigration"
|
||
|
||
- id: "immigration"
|
||
label: "immigration"
|
||
|
||
# =============================================================================
|
||
# GLM ANNOTATOR OUTPUT SCHEMA UPDATE
|
||
# =============================================================================
|
||
#
|
||
# Extended output schema for GLM-4.6 annotator to include family relationships
|
||
# and biographical properties.
|
||
# =============================================================================
|
||
|
||
glm_extended_output_schema:
|
||
description: |
|
||
Extended JSON output schema that includes all PiCo properties.
|
||
This supplements the core system_prompt output format.
|
||
|
||
persons_extended:
|
||
description: "Extended person object with all PiCo properties"
|
||
schema:
|
||
pnv_name:
|
||
literalName: "string"
|
||
givenName: "string|null"
|
||
patronym: "string|null"
|
||
surnamePrefix: "string|null"
|
||
baseSurname: "string|null"
|
||
honorificPrefix: "string|null"
|
||
honorificSuffix: "string|null"
|
||
initials: "string|null"
|
||
|
||
biographical:
|
||
birth_date: "ISO date|null"
|
||
death_date: "ISO date|null"
|
||
birth_place: "string|null"
|
||
death_place: "string|null"
|
||
gender: "Male|Female|null"
|
||
age: "string|null"
|
||
religion: "string|null"
|
||
deceased: "boolean|null"
|
||
address: "string|null"
|
||
floruit: "string|null"
|
||
|
||
roles: "array of role objects"
|
||
|
||
family_relationships:
|
||
parent: "array of person references"
|
||
children: "array of person references"
|
||
spouse: "array of person references"
|
||
sibling: "array of person references"
|
||
grandparent: "array of person references"
|
||
grandchild: "array of person references"
|
||
uncle_aunt: "array of person references"
|
||
nephew_niece: "array of person references"
|
||
cousin: "array of person references"
|
||
stepparent: "array of person references"
|
||
stepchild: "array of person references"
|
||
stepsibling: "array of person references"
|
||
half_sibling: "array of person references"
|
||
foster_parent: "array of person references"
|
||
foster_child: "array of person references"
|
||
godparent: "array of person references"
|
||
godchild: "array of person references"
|
||
parent_in_law: "array of person references"
|
||
child_in_law: "array of person references"
|
||
sibling_in_law: "array of person references"
|
||
previous_partner: "array of person references"
|
||
widow_of: "person reference|null"
|
||
|
||
context: "string|null"
|
||
|
||
# =============================================================================
|
||
# CH-ANNOTATOR HYPERNYM INTEGRATION UPDATE
|
||
# =============================================================================
|
||
#
|
||
# Updated hypernym mappings to include reconstruction pattern.
|
||
# =============================================================================
|
||
|
||
extended_hypernym_mapping:
|
||
description: |
|
||
Extended mappings between PiCo classes and CH-Annotator hypernyms,
|
||
including the reconstruction pattern.
|
||
|
||
mappings:
|
||
# Observation level
|
||
- pico_class: "pico:PersonObservation"
|
||
ch_hypernym: "AGT.PER"
|
||
ch_code: "AGT.PER"
|
||
note: "Source-bound person mention"
|
||
|
||
- pico_class: "pico:PersonObservation"
|
||
ch_hypernym: "AGT.STF"
|
||
ch_code: "AGT.STF"
|
||
condition: "When person has organizational role"
|
||
note: "Staff member observation"
|
||
|
||
# Reconstruction level
|
||
- pico_class: "pico:PersonReconstruction"
|
||
ch_hypernym: "AGT.PER"
|
||
ch_code: "AGT.PER"
|
||
note: "Reconstructed person entity"
|
||
linking: true
|
||
linking_sources: ["Wikidata", "VIAF", "ISNI"]
|
||
|
||
# Name components
|
||
- pico_class: "pnv:PersonName"
|
||
ch_hypernym: "APP.NAM"
|
||
ch_code: "APP.NAM"
|
||
note: "Structured name"
|
||
|
||
# Roles
|
||
- pico_class: "pico:hasRole"
|
||
ch_hypernym: "ROL"
|
||
ch_code: "ROL"
|
||
note: "Role in source"
|
||
|
||
# Family relationships
|
||
- pico_class: "sdo:parent"
|
||
ch_hypernym: "AGT.PER"
|
||
relationship_type: "family"
|
||
note: "Parent relationship"
|
||
|
||
- pico_class: "sdo:spouse"
|
||
ch_hypernym: "AGT.PER"
|
||
relationship_type: "family"
|
||
note: "Spouse relationship"
|
||
|
||
- pico_class: "pico:hasGodparent"
|
||
ch_hypernym: "AGT.PER"
|
||
relationship_type: "ritual_kinship"
|
||
note: "Godparent relationship (common in historical records)"
|
||
|
||
# Sources
|
||
- pico_class: "sdo:ArchiveComponent"
|
||
ch_hypernym: "WRK.DOC"
|
||
ch_code: "WRK.DOC"
|
||
note: "Source document"
|
||
|
||
# Provenance
|
||
- pico_class: "prov:Activity"
|
||
ch_hypernym: null
|
||
note: "Not directly annotated; tracked in provenance metadata"
|
||
|
||
- pico_class: "prov:Agent"
|
||
ch_hypernym: "AGT"
|
||
ch_code: "AGT"
|
||
note: "Extraction/reconstruction agent"
|
||
|
||
# =============================================================================
|
||
# HISTORICAL SOURCE EXTRACTION EXAMPLES
|
||
# =============================================================================
|
||
#
|
||
# Comprehensive examples showing extraction from different historical source types.
|
||
# These demonstrate the full PiCo model including family relationships.
|
||
# =============================================================================
|
||
|
||
historical_extraction_examples:
|
||
description: |
|
||
These examples demonstrate extraction from common historical source types,
|
||
showing how to capture family relationships, biographical data, and roles
|
||
according to the PiCo model.
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Example 1: Dutch Marriage Certificate (Burgerlijke Stand)
|
||
# ---------------------------------------------------------------------------
|
||
|
||
marriage_certificate_example:
|
||
source_type: "civil_registration"
|
||
source_text: |
|
||
Heden den elfden November achttien honderd vijf en tachtig, zijn voor ons
|
||
Ambtenaar van den Burgerlijken Stand der gemeente Haarlem, verschenen:
|
||
Cornelis Johannes Koppen, oud dertig jaren, schilder, geboren te Haarlem,
|
||
wonende alhier, meerderjarige zoon van wijlen Pieter Koppen en van
|
||
Anna Maria Brouwer, zonder beroep, wonende alhier;
|
||
en Anna Maria Visser, oud zeven en twintig jaren, zonder beroep, geboren
|
||
te Amsterdam, wonende alhier, meerderjarige dochter van Jan Visser,
|
||
koopman, en van wijlen Cornelia de Vries.
|
||
|
||
Als getuigen waren tegenwoordig: Hendrik Koppen, oud vijf en dertig jaren,
|
||
schilder, broeder van den bruidegom; en Willem Visser, oud twee en dertig
|
||
jaren, timmerman, broeder van de bruid.
|
||
|
||
expected_output:
|
||
pico_observation:
|
||
observation_id: "bs_haarlem_1885_marriage_321"
|
||
observed_at: "2025-12-12T10:00:00Z"
|
||
source_type: "civil_registration"
|
||
source_reference: "BS Marriage Haarlem, November 11, 1885, certificate 321"
|
||
|
||
persons:
|
||
- person_index: 0
|
||
pnv_name:
|
||
literalName: "Cornelis Johannes Koppen"
|
||
givenName: "Cornelis Johannes"
|
||
baseSurname: "Koppen"
|
||
roles:
|
||
- role_title: "schilder"
|
||
role_in_source: "groom"
|
||
biographical:
|
||
age: "30"
|
||
birth_place: "Haarlem"
|
||
address: "Haarlem"
|
||
family_relationships:
|
||
parent:
|
||
- person_index: 2
|
||
target_name: "Pieter Koppen"
|
||
- person_index: 3
|
||
target_name: "Anna Maria Brouwer"
|
||
spouse:
|
||
- person_index: 1
|
||
target_name: "Anna Maria Visser"
|
||
sibling:
|
||
- person_index: 6
|
||
target_name: "Hendrik Koppen"
|
||
|
||
- person_index: 1
|
||
pnv_name:
|
||
literalName: "Anna Maria Visser"
|
||
givenName: "Anna Maria"
|
||
baseSurname: "Visser"
|
||
roles:
|
||
- role_in_source: "bride"
|
||
biographical:
|
||
age: "27"
|
||
birth_place: "Amsterdam"
|
||
address: "Haarlem"
|
||
family_relationships:
|
||
parent:
|
||
- person_index: 4
|
||
target_name: "Jan Visser"
|
||
- person_index: 5
|
||
target_name: "Cornelia de Vries"
|
||
spouse:
|
||
- person_index: 0
|
||
target_name: "Cornelis Johannes Koppen"
|
||
sibling:
|
||
- person_index: 7
|
||
target_name: "Willem Visser"
|
||
|
||
- person_index: 2
|
||
pnv_name:
|
||
literalName: "Pieter Koppen"
|
||
givenName: "Pieter"
|
||
baseSurname: "Koppen"
|
||
biographical:
|
||
deceased: true
|
||
family_relationships:
|
||
children:
|
||
- person_index: 0
|
||
target_name: "Cornelis Johannes Koppen"
|
||
- person_index: 6
|
||
target_name: "Hendrik Koppen"
|
||
spouse:
|
||
- person_index: 3
|
||
target_name: "Anna Maria Brouwer"
|
||
|
||
- person_index: 3
|
||
pnv_name:
|
||
literalName: "Anna Maria Brouwer"
|
||
givenName: "Anna Maria"
|
||
baseSurname: "Brouwer"
|
||
roles:
|
||
- role_title: "zonder beroep"
|
||
biographical:
|
||
address: "Haarlem"
|
||
family_relationships:
|
||
children:
|
||
- person_index: 0
|
||
target_name: "Cornelis Johannes Koppen"
|
||
- person_index: 6
|
||
target_name: "Hendrik Koppen"
|
||
widow_of:
|
||
person_index: 2
|
||
target_name: "Pieter Koppen"
|
||
|
||
- person_index: 4
|
||
pnv_name:
|
||
literalName: "Jan Visser"
|
||
givenName: "Jan"
|
||
baseSurname: "Visser"
|
||
roles:
|
||
- role_title: "koopman"
|
||
family_relationships:
|
||
children:
|
||
- person_index: 1
|
||
target_name: "Anna Maria Visser"
|
||
- person_index: 7
|
||
target_name: "Willem Visser"
|
||
spouse:
|
||
- person_index: 5
|
||
target_name: "Cornelia de Vries"
|
||
|
||
- person_index: 5
|
||
pnv_name:
|
||
literalName: "Cornelia de Vries"
|
||
givenName: "Cornelia"
|
||
surnamePrefix: "de"
|
||
baseSurname: "Vries"
|
||
biographical:
|
||
deceased: true
|
||
family_relationships:
|
||
children:
|
||
- person_index: 1
|
||
target_name: "Anna Maria Visser"
|
||
- person_index: 7
|
||
target_name: "Willem Visser"
|
||
spouse:
|
||
- person_index: 4
|
||
target_name: "Jan Visser"
|
||
|
||
- person_index: 6
|
||
pnv_name:
|
||
literalName: "Hendrik Koppen"
|
||
givenName: "Hendrik"
|
||
baseSurname: "Koppen"
|
||
roles:
|
||
- role_title: "schilder"
|
||
role_in_source: "witness"
|
||
biographical:
|
||
age: "35"
|
||
family_relationships:
|
||
sibling:
|
||
- person_index: 0
|
||
target_name: "Cornelis Johannes Koppen"
|
||
parent:
|
||
- person_index: 2
|
||
target_name: "Pieter Koppen"
|
||
- person_index: 3
|
||
target_name: "Anna Maria Brouwer"
|
||
|
||
- person_index: 7
|
||
pnv_name:
|
||
literalName: "Willem Visser"
|
||
givenName: "Willem"
|
||
baseSurname: "Visser"
|
||
roles:
|
||
- role_title: "timmerman"
|
||
role_in_source: "witness"
|
||
biographical:
|
||
age: "32"
|
||
family_relationships:
|
||
sibling:
|
||
- person_index: 1
|
||
target_name: "Anna Maria Visser"
|
||
parent:
|
||
- person_index: 4
|
||
target_name: "Jan Visser"
|
||
- person_index: 5
|
||
target_name: "Cornelia de Vries"
|
||
|
||
temporal_references:
|
||
- expression: "den elfden November achttien honderd vijf en tachtig"
|
||
normalized: "1885-11-11"
|
||
type: "DATE"
|
||
|
||
locations_mentioned:
|
||
- name: "Haarlem"
|
||
type: "city"
|
||
- name: "Amsterdam"
|
||
type: "city"
|
||
|
||
provenance:
|
||
data_status: "SYNTHETIC_EXAMPLE"
|
||
notes: |
|
||
This example uses synthetic data based on authentic Dutch civil
|
||
registry (Burgerlijke Stand) marriage certificate formulae for
|
||
demonstration purposes. Names, dates, and locations are fictional
|
||
but follow authentic 19th-century patterns.
|
||
For real examples, see PROVENANCE_SOURCES.md.
|
||
|
||
related_real_sources:
|
||
- archive: "Centraal Bureau voor Genealogie (CBG)"
|
||
project: "WieWasWie"
|
||
digital_url: "https://www.wiewaswie.nl/"
|
||
document_type: "Birth, marriage, death certificates"
|
||
period: "1811-present (civil); 1600s+ (church)"
|
||
language: "Dutch"
|
||
license: "Subscription / Free at archives"
|
||
|
||
- archive: "Noord-Hollands Archief"
|
||
coverage: "Civil registry from 1811, church records from 1600s"
|
||
location: "Haarlem, Netherlands"
|
||
document_types: "Dutch civil registry records"
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Example 2: Early Modern Notarial Protocol Index Entry
|
||
# ---------------------------------------------------------------------------
|
||
|
||
notarial_index_example:
|
||
source_type: "historical_indices"
|
||
source_text: |
|
||
Notarial Archive Amsterdam, inv. 5075/1234
|
||
30 January 1680
|
||
|
||
Before notary Pieter van der Meer appeared:
|
||
Jacob Janszoon van der Hoeven, merchant of this city,
|
||
with his wife Maritgen Claes, for themselves and as
|
||
guardians (voogden) of the minor children of the late
|
||
Claes Jacobsz and Aeltgen Pieters, namely:
|
||
- Jan Claeszoon, aged about 16 years
|
||
- Trijntgen Claesdr, aged about 12 years
|
||
|
||
Witnesses: Hendrick Jansz, baker, and Cornelis Pietersz,
|
||
schoolmaster, both of this city.
|
||
|
||
expected_output:
|
||
pico_observation:
|
||
observation_id: "na_amsterdam_5075_1234"
|
||
observed_at: "2025-12-12T10:00:00Z"
|
||
source_type: "historical_indices"
|
||
source_reference: "Notarial Archive Amsterdam, inv. 5075/1234, 30 January 1680"
|
||
|
||
persons:
|
||
- person_index: 0
|
||
pnv_name:
|
||
literalName: "Jacob Janszoon van der Hoeven"
|
||
givenName: "Jacob"
|
||
patronym: "Janszoon"
|
||
surnamePrefix: "van der"
|
||
baseSurname: "Hoeven"
|
||
roles:
|
||
- role_title: "merchant"
|
||
role_in_source: "declarant"
|
||
- role_title: "voogd"
|
||
role_in_source: null
|
||
biographical:
|
||
address: "Amsterdam"
|
||
family_relationships:
|
||
spouse:
|
||
- person_index: 1
|
||
target_name: "Maritgen Claes"
|
||
|
||
- person_index: 1
|
||
pnv_name:
|
||
literalName: "Maritgen Claes"
|
||
givenName: "Maritgen"
|
||
patronym: "Claes"
|
||
roles:
|
||
- role_in_source: "declarant"
|
||
- role_title: "voogd"
|
||
family_relationships:
|
||
spouse:
|
||
- person_index: 0
|
||
target_name: "Jacob Janszoon van der Hoeven"
|
||
|
||
- person_index: 2
|
||
pnv_name:
|
||
literalName: "Claes Jacobsz"
|
||
givenName: "Claes"
|
||
patronym: "Jacobsz"
|
||
biographical:
|
||
deceased: true
|
||
family_relationships:
|
||
spouse:
|
||
- person_index: 3
|
||
target_name: "Aeltgen Pieters"
|
||
children:
|
||
- person_index: 4
|
||
target_name: "Jan Claeszoon"
|
||
- person_index: 5
|
||
target_name: "Trijntgen Claesdr"
|
||
|
||
- person_index: 3
|
||
pnv_name:
|
||
literalName: "Aeltgen Pieters"
|
||
givenName: "Aeltgen"
|
||
patronym: "Pieters"
|
||
biographical:
|
||
deceased: true
|
||
family_relationships:
|
||
spouse:
|
||
- person_index: 2
|
||
target_name: "Claes Jacobsz"
|
||
children:
|
||
- person_index: 4
|
||
target_name: "Jan Claeszoon"
|
||
- person_index: 5
|
||
target_name: "Trijntgen Claesdr"
|
||
|
||
- person_index: 4
|
||
pnv_name:
|
||
literalName: "Jan Claeszoon"
|
||
givenName: "Jan"
|
||
patronym: "Claeszoon"
|
||
roles:
|
||
- role_in_source: "child"
|
||
biographical:
|
||
age: "about 16"
|
||
family_relationships:
|
||
parent:
|
||
- person_index: 2
|
||
target_name: "Claes Jacobsz"
|
||
- person_index: 3
|
||
target_name: "Aeltgen Pieters"
|
||
sibling:
|
||
- person_index: 5
|
||
target_name: "Trijntgen Claesdr"
|
||
|
||
- person_index: 5
|
||
pnv_name:
|
||
literalName: "Trijntgen Claesdr"
|
||
givenName: "Trijntgen"
|
||
patronym: "Claesdr"
|
||
roles:
|
||
- role_in_source: "child"
|
||
biographical:
|
||
age: "about 12"
|
||
gender: "Female"
|
||
family_relationships:
|
||
parent:
|
||
- person_index: 2
|
||
target_name: "Claes Jacobsz"
|
||
- person_index: 3
|
||
target_name: "Aeltgen Pieters"
|
||
sibling:
|
||
- person_index: 4
|
||
target_name: "Jan Claeszoon"
|
||
|
||
- person_index: 6
|
||
pnv_name:
|
||
literalName: "Pieter van der Meer"
|
||
givenName: "Pieter"
|
||
surnamePrefix: "van der"
|
||
baseSurname: "Meer"
|
||
roles:
|
||
- role_title: "notary"
|
||
|
||
- person_index: 7
|
||
pnv_name:
|
||
literalName: "Hendrick Jansz"
|
||
givenName: "Hendrick"
|
||
patronym: "Jansz"
|
||
roles:
|
||
- role_title: "baker"
|
||
role_in_source: "witness"
|
||
biographical:
|
||
address: "Amsterdam"
|
||
|
||
- person_index: 8
|
||
pnv_name:
|
||
literalName: "Cornelis Pietersz"
|
||
givenName: "Cornelis"
|
||
patronym: "Pietersz"
|
||
roles:
|
||
- role_title: "schoolmaster"
|
||
role_in_source: "witness"
|
||
biographical:
|
||
address: "Amsterdam"
|
||
|
||
temporal_references:
|
||
- expression: "30 January 1680"
|
||
normalized: "1680-01-30"
|
||
type: "DATE"
|
||
|
||
locations_mentioned:
|
||
- name: "Amsterdam"
|
||
type: "city"
|
||
|
||
provenance:
|
||
data_status: "SYNTHETIC_EXAMPLE"
|
||
notes: |
|
||
This example uses synthetic data based on authentic early modern
|
||
notarial protocol index entry formulae for demonstration purposes.
|
||
Names, dates, and locations are fictional but follow authentic
|
||
17th-century Dutch notarial patterns.
|
||
For real examples, see PROVENANCE_SOURCES.md.
|
||
|
||
related_real_sources:
|
||
- archive: "Stadsarchief Amsterdam"
|
||
collection: "Notarial Archives (Notariële Archieven)"
|
||
document_type: "Notarial protocols, contracts, testaments"
|
||
period: "1578-1915"
|
||
language: "Dutch, Latin"
|
||
notes: "Largest notarial archive in the Netherlands"
|
||
|
||
- project: "TICCLAT (Transliteration of Early Modern Dutch Notarial Archives)"
|
||
coverage: "Amsterdam notarial indices"
|
||
period: "17th-18th century"
|
||
notes: "Machine-readable indices to notarial protocols"
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Example 3: Church Baptismal Record with Godparents
|
||
# ---------------------------------------------------------------------------
|
||
|
||
baptism_record_example:
|
||
source_type: "church_records"
|
||
source_text: |
|
||
Den 15en Meij 1702 is gedoopt
|
||
Johanna, dochter van Willem Hendriksen en Geertruijd Jans,
|
||
getuijgen waren de E. Heer Jan Willem van Beverwijck
|
||
ende Juffrou Maria van Loon, huijsvrouw van de heer
|
||
Pieter Anthonisz Verschoor.
|
||
|
||
expected_output:
|
||
pico_observation:
|
||
observation_id: "dtb_amsterdam_1702_baptism_johanna"
|
||
observed_at: "2025-12-12T10:00:00Z"
|
||
source_type: "church_records"
|
||
source_reference: "DTB Amsterdam, 15 May 1702"
|
||
|
||
persons:
|
||
- person_index: 0
|
||
pnv_name:
|
||
literalName: "Johanna"
|
||
givenName: "Johanna"
|
||
roles:
|
||
- role_in_source: "child"
|
||
biographical:
|
||
gender: "Female"
|
||
family_relationships:
|
||
parent:
|
||
- person_index: 1
|
||
target_name: "Willem Hendriksen"
|
||
- person_index: 2
|
||
target_name: "Geertruijd Jans"
|
||
godparent:
|
||
- person_index: 3
|
||
target_name: "Jan Willem van Beverwijck"
|
||
- person_index: 4
|
||
target_name: "Maria van Loon"
|
||
|
||
- person_index: 1
|
||
pnv_name:
|
||
literalName: "Willem Hendriksen"
|
||
givenName: "Willem"
|
||
patronym: "Hendriksen"
|
||
biographical:
|
||
gender: "Male"
|
||
family_relationships:
|
||
children:
|
||
- person_index: 0
|
||
target_name: "Johanna"
|
||
spouse:
|
||
- person_index: 2
|
||
target_name: "Geertruijd Jans"
|
||
|
||
- person_index: 2
|
||
pnv_name:
|
||
literalName: "Geertruijd Jans"
|
||
givenName: "Geertruijd"
|
||
patronym: "Jans"
|
||
biographical:
|
||
gender: "Female"
|
||
family_relationships:
|
||
children:
|
||
- person_index: 0
|
||
target_name: "Johanna"
|
||
spouse:
|
||
- person_index: 1
|
||
target_name: "Willem Hendriksen"
|
||
|
||
- person_index: 3
|
||
pnv_name:
|
||
literalName: "Jan Willem van Beverwijck"
|
||
givenName: "Jan Willem"
|
||
surnamePrefix: "van"
|
||
baseSurname: "Beverwijck"
|
||
honorificPrefix: "de E. Heer"
|
||
roles:
|
||
- role_in_source: "witness"
|
||
biographical:
|
||
gender: "Male"
|
||
family_relationships:
|
||
godchild:
|
||
- person_index: 0
|
||
target_name: "Johanna"
|
||
|
||
- person_index: 4
|
||
pnv_name:
|
||
literalName: "Maria van Loon"
|
||
givenName: "Maria"
|
||
surnamePrefix: "van"
|
||
baseSurname: "Loon"
|
||
honorificPrefix: "Juffrou"
|
||
roles:
|
||
- role_in_source: "witness"
|
||
biographical:
|
||
gender: "Female"
|
||
family_relationships:
|
||
godchild:
|
||
- person_index: 0
|
||
target_name: "Johanna"
|
||
spouse:
|
||
- person_index: 5
|
||
target_name: "Pieter Anthonisz Verschoor"
|
||
|
||
- person_index: 5
|
||
pnv_name:
|
||
literalName: "Pieter Anthonisz Verschoor"
|
||
givenName: "Pieter"
|
||
patronym: "Anthonisz"
|
||
baseSurname: "Verschoor"
|
||
honorificPrefix: "de heer"
|
||
biographical:
|
||
gender: "Male"
|
||
family_relationships:
|
||
spouse:
|
||
- person_index: 4
|
||
target_name: "Maria van Loon"
|
||
|
||
temporal_references:
|
||
- expression: "Den 15en Meij 1702"
|
||
normalized: "1702-05-15"
|
||
type: "DATE"
|
||
|
||
provenance:
|
||
data_status: "SYNTHETIC_EXAMPLE"
|
||
notes: |
|
||
This example uses synthetic data based on authentic Dutch Reformed
|
||
Church (Nederlandse Hervormde Kerk) baptismal register formulae for
|
||
demonstration purposes. Names, dates, and locations are fictional
|
||
but follow authentic early 18th-century patterns.
|
||
For real examples, see PROVENANCE_SOURCES.md.
|
||
|
||
related_real_sources:
|
||
- archive: "Various Dutch Regional Archives"
|
||
collection: "Doop-, Trouw- en Begraafregisters (DTB)"
|
||
document_type: "Church baptism, marriage, burial records"
|
||
period: "1600s-1811 (before civil registration)"
|
||
language: "Dutch"
|
||
notes: "Pre-1811 vital records maintained by churches"
|
||
|
||
- archive: "FamilySearch"
|
||
collection: "Netherlands, Church Records"
|
||
wiki_url: "https://www.familysearch.org/en/wiki/Netherlands_Church_Records"
|
||
document_type: "Dutch church baptisms"
|
||
license: "Free with registration"
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Example 4: Modern LinkedIn Staff Profile
|
||
# ---------------------------------------------------------------------------
|
||
|
||
linkedin_profile_example:
|
||
source_type: "modern_digital"
|
||
source_text: |
|
||
Dr. Maria van den Berg
|
||
Director of Collections | Rijksmuseum
|
||
Amsterdam, Netherlands
|
||
|
||
About:
|
||
Leading the collections management team at the Rijksmuseum since 2018.
|
||
Previously Head Curator at the Van Gogh Museum (2012-2018).
|
||
PhD in Art History, University of Amsterdam.
|
||
|
||
Experience:
|
||
- Director of Collections, Rijksmuseum (2018-present)
|
||
- Head Curator, Van Gogh Museum (2012-2018)
|
||
- Assistant Curator, Stedelijk Museum (2008-2012)
|
||
|
||
Education:
|
||
- PhD Art History, University of Amsterdam (2008)
|
||
- MA Museum Studies, University of Amsterdam (2003)
|
||
|
||
expected_output:
|
||
pico_observation:
|
||
observation_id: "linkedin_maria_van_den_berg_2025"
|
||
observed_at: "2025-12-12T10:00:00Z"
|
||
source_type: "modern_digital"
|
||
source_reference: "https://linkedin.com/in/mariavandenberg"
|
||
|
||
persons:
|
||
- person_index: 0
|
||
pnv_name:
|
||
literalName: "Dr. Maria van den Berg"
|
||
givenName: "Maria"
|
||
surnamePrefix: "van den"
|
||
baseSurname: "Berg"
|
||
honorificPrefix: "Dr."
|
||
roles:
|
||
- role_title: "Director of Collections"
|
||
organization: "Rijksmuseum"
|
||
period: "2018-present"
|
||
heritage_relevant: true
|
||
heritage_type: "M"
|
||
- role_title: "Head Curator"
|
||
organization: "Van Gogh Museum"
|
||
period: "2012-2018"
|
||
heritage_relevant: true
|
||
heritage_type: "M"
|
||
- role_title: "Assistant Curator"
|
||
organization: "Stedelijk Museum"
|
||
period: "2008-2012"
|
||
heritage_relevant: true
|
||
heritage_type: "M"
|
||
biographical:
|
||
address: "Amsterdam, Netherlands"
|
||
family_relationships: {}
|
||
context: "Heritage sector professional with museum career"
|
||
|
||
organizations_mentioned:
|
||
- name: "Rijksmuseum"
|
||
type: "M"
|
||
role_in_source: "employer"
|
||
- name: "Van Gogh Museum"
|
||
type: "M"
|
||
role_in_source: "employer"
|
||
- name: "Stedelijk Museum"
|
||
type: "M"
|
||
role_in_source: "employer"
|
||
- name: "University of Amsterdam"
|
||
type: "E"
|
||
role_in_source: "education"
|
||
|
||
locations_mentioned:
|
||
- name: "Amsterdam"
|
||
type: "city"
|
||
- name: "Netherlands"
|
||
type: "country"
|
||
|
||
provenance:
|
||
data_status: "SYNTHETIC_EXAMPLE"
|
||
notes: |
|
||
This example uses synthetic data based on modern LinkedIn profile
|
||
formats for demonstration purposes. The profile name, institution,
|
||
and biographical details are entirely fictional. LinkedIn profiles
|
||
represent a modern source type for person-in-context observations,
|
||
contrasting with the historical document examples in this module.
|
||
|
||
source_context:
|
||
platform: "LinkedIn"
|
||
data_type: "Modern professional networking profile"
|
||
privacy_note: |
|
||
When extracting real LinkedIn data, ensure compliance with
|
||
LinkedIn Terms of Service, GDPR, and applicable privacy laws.
|
||
This synthetic example demonstrates extraction patterns only.
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Example 5: Arabic Waqf Document (Endowment Record)
|
||
# ---------------------------------------------------------------------------
|
||
|
||
arabic_waqf_example:
|
||
source_type: "archival_descriptions"
|
||
language: "Arabic"
|
||
description: |
|
||
Example of a waqf (religious endowment) document from an Islamic archive.
|
||
Waqf documents record property endowments for religious/charitable purposes
|
||
and typically name the founder, beneficiaries, and witnesses.
|
||
|
||
source_text: |
|
||
بسم الله الرحمن الرحيم
|
||
هذا ما وقف وحبس وسبل وأبد المرحوم الحاج أحمد بن محمد العمري، تاجر بمدينة
|
||
حلب الشهباء، ابن المرحوم محمد بن عبد الله العمري. وقف جميع داره الكائنة
|
||
بمحلة الجديدة على أولاده وأولاد أولاده ذكوراً وإناثاً. وإن انقرضوا لا سمح
|
||
الله فعلى فقراء المسلمين. وشهد على ذلك الشهود: الحاج إبراهيم بن يوسف
|
||
التركماني، والسيد علي بن حسين الحلبي. وكتب في شهر رجب سنة ألف ومائتين
|
||
وخمس وعشرين هجرية.
|
||
|
||
[Translation: In the name of God, the Compassionate, the Merciful.
|
||
This is what the late al-Hajj Ahmad ibn Muhammad al-'Umari, merchant
|
||
in the city of Aleppo, son of the late Muhammad ibn Abdullah al-'Umari,
|
||
has endowed, dedicated, and perpetuated. He endowed his entire house
|
||
located in the al-Jadida neighborhood for his children and grandchildren,
|
||
male and female. If they cease to exist, God forbid, then for the poor
|
||
Muslims. Witnessed by: al-Hajj Ibrahim ibn Yusuf al-Turkmani, and
|
||
al-Sayyid Ali ibn Husayn al-Halabi. Written in the month of Rajab,
|
||
year 1225 Hijri (1810 CE).]
|
||
|
||
expected_output:
|
||
pico_observation:
|
||
observation_id: "waqf_aleppo_1225h_ahmad_umari"
|
||
observed_at: "2025-12-12T10:00:00Z"
|
||
source_type: "archival_descriptions"
|
||
source_reference: "Waqf document, Aleppo, Rajab 1225 AH (1810 CE)"
|
||
|
||
persons:
|
||
- person_index: 0
|
||
pnv_name:
|
||
literalName: "الحاج أحمد بن محمد العمري"
|
||
literalName_romanized: "al-Hajj Ahmad ibn Muhammad al-'Umari"
|
||
givenName: "أحمد"
|
||
givenName_romanized: "Ahmad"
|
||
patronym: "محمد"
|
||
patronym_romanized: "Muhammad"
|
||
baseSurname: "العمري"
|
||
baseSurname_romanized: "al-'Umari"
|
||
honorificPrefix: "الحاج"
|
||
honorificPrefix_romanized: "al-Hajj"
|
||
roles:
|
||
- role_title: "تاجر"
|
||
role_title_romanized: "merchant"
|
||
role_in_source: "founder"
|
||
biographical:
|
||
deceased: true
|
||
address: "حلب الشهباء (Aleppo)"
|
||
family_relationships:
|
||
parent:
|
||
- person_index: 1
|
||
target_name: "محمد بن عبد الله العمري"
|
||
context: "Waqf founder (واقف)"
|
||
|
||
- person_index: 1
|
||
pnv_name:
|
||
literalName: "محمد بن عبد الله العمري"
|
||
literalName_romanized: "Muhammad ibn Abdullah al-'Umari"
|
||
givenName: "محمد"
|
||
givenName_romanized: "Muhammad"
|
||
patronym: "عبد الله"
|
||
patronym_romanized: "Abdullah"
|
||
baseSurname: "العمري"
|
||
baseSurname_romanized: "al-'Umari"
|
||
honorificPrefix: "المرحوم"
|
||
honorificPrefix_romanized: "the late"
|
||
biographical:
|
||
deceased: true
|
||
family_relationships:
|
||
children:
|
||
- person_index: 0
|
||
target_name: "أحمد بن محمد العمري"
|
||
context: "Father of the founder"
|
||
|
||
- person_index: 2
|
||
pnv_name:
|
||
literalName: "الحاج إبراهيم بن يوسف التركماني"
|
||
literalName_romanized: "al-Hajj Ibrahim ibn Yusuf al-Turkmani"
|
||
givenName: "إبراهيم"
|
||
givenName_romanized: "Ibrahim"
|
||
patronym: "يوسف"
|
||
patronym_romanized: "Yusuf"
|
||
baseSurname: "التركماني"
|
||
baseSurname_romanized: "al-Turkmani"
|
||
honorificPrefix: "الحاج"
|
||
honorificPrefix_romanized: "al-Hajj"
|
||
roles:
|
||
- role_in_source: "witness"
|
||
family_relationships: {}
|
||
context: "Witness to the endowment"
|
||
|
||
- person_index: 3
|
||
pnv_name:
|
||
literalName: "السيد علي بن حسين الحلبي"
|
||
literalName_romanized: "al-Sayyid Ali ibn Husayn al-Halabi"
|
||
givenName: "علي"
|
||
givenName_romanized: "Ali"
|
||
patronym: "حسين"
|
||
patronym_romanized: "Husayn"
|
||
baseSurname: "الحلبي"
|
||
baseSurname_romanized: "al-Halabi"
|
||
honorificPrefix: "السيد"
|
||
honorificPrefix_romanized: "al-Sayyid"
|
||
roles:
|
||
- role_in_source: "witness"
|
||
family_relationships: {}
|
||
context: "Witness to the endowment"
|
||
|
||
temporal_references:
|
||
- expression: "شهر رجب سنة ألف ومائتين وخمس وعشرين هجرية"
|
||
expression_romanized: "month of Rajab, year 1225 Hijri"
|
||
normalized: "1810-07" # Approximate Gregorian equivalent
|
||
calendar: "Hijri"
|
||
type: "DATE"
|
||
|
||
locations_mentioned:
|
||
- name: "حلب الشهباء"
|
||
name_romanized: "Aleppo"
|
||
type: "city"
|
||
- name: "محلة الجديدة"
|
||
name_romanized: "al-Jadida neighborhood"
|
||
type: "neighborhood"
|
||
|
||
arabic_naming_notes: |
|
||
Arabic naming conventions demonstrated:
|
||
- ابن/بن (ibn/bin): patronymic "son of"
|
||
- الحاج (al-Hajj): honorific for one who completed pilgrimage
|
||
- السيد (al-Sayyid): honorific denoting descent from Prophet Muhammad
|
||
- المرحوم (al-marhum): "the late" (deceased)
|
||
- نسبة (nisba): geographic/tribal surname (العمري - from 'Umar tribe,
|
||
التركماني - Turkman origin, الحلبي - from Aleppo)
|
||
|
||
provenance:
|
||
data_status: "SYNTHETIC_EXAMPLE"
|
||
notes: |
|
||
This example uses synthetic data based on standard waqf document formulae
|
||
for demonstration purposes. Names, dates, and property details are fictional.
|
||
For real examples, see PROVENANCE_SOURCES.md.
|
||
|
||
related_real_sources:
|
||
- archive: "Cambridge University Library"
|
||
collection: "Islamic Manuscripts"
|
||
digital_url: "https://cudl.lib.cam.ac.uk/collections/islamic"
|
||
document_types: "Waqfiyya, legal documents"
|
||
period: "8th-20th century CE"
|
||
license: "CC BY-NC 4.0"
|
||
|
||
- archive: "University of Pennsylvania Libraries"
|
||
collection: "Manuscripts of the Muslim World"
|
||
digital_url: "https://openn.library.upenn.edu/html/muslimworld_contents.html"
|
||
document_types: "Waqfiyya, Quranic manuscripts, legal documents"
|
||
license: "Public Domain / CC0"
|
||
|
||
- archive: "Singapore National Heritage Board"
|
||
accession_number: "1115401"
|
||
digital_url: "https://www.roots.gov.sg/Collection-Landing/listing/1115401"
|
||
document_type: "Waqf document"
|
||
donor: "Muhammad b. Abd al-Ghani"
|
||
properties: "Istanbul (various locations)"
|
||
|
||
# =============================================================================
|
||
# EXAMPLE 6: Hebrew Ketubah - Marriage of Mosheh & Rivkah (Mashhad, Iran, 1896)
|
||
# =============================================================================
|
||
#
|
||
# REAL HISTORICAL DATA from Yale University Beinecke Library
|
||
#
|
||
# Source type: ketubah (Jewish marriage contract)
|
||
# Language: Hebrew/Aramaic
|
||
# Date: 23 Elul 5656 AM (September 1, 1896 CE)
|
||
# Location: Mashhad, Iran
|
||
# Call Number: Hebrew MSS suppl 194 (Broadside)
|
||
#
|
||
# This is a REAL ketubah with verified provenance from Yale's digital collection.
|
||
# The Mashhad Jewish community had a unique history as "crypto-Jews" after
|
||
# forced conversion in 1839, making this document culturally significant.
|
||
# =============================================================================
|
||
|
||
example_6_hebrew_ketubah:
|
||
description: |
|
||
A ketubah (כתובה) is a Jewish marriage contract written in Aramaic with Hebrew
|
||
elements. This REAL example from Mashhad, Iran demonstrates Persian Jewish
|
||
traditions with elaborate decorative elements.
|
||
|
||
Historical context: The Jewish community of Mashhad was unique - after forced
|
||
conversion to Islam in 1839 (the Allahdad pogrom), many continued practicing
|
||
Judaism in secret as "Jadid al-Islam" (new Muslims). By 1896, some families
|
||
were more openly practicing Judaism, as evidenced by this elaborate ketubah.
|
||
|
||
Key features documented:
|
||
- Groom and bride names with patronymics (בן/בת - son/daughter of)
|
||
- Persian Jewish artistic traditions (floral patterns, colored rules)
|
||
- Hebrew date with month, day, and year from Creation
|
||
- Isaiah 61:10 verse as blessing
|
||
- Physical dimensions: 53 x 37 cm
|
||
|
||
source_text: |
|
||
[Note: Full text not transcribed from manuscript. Key readable elements:]
|
||
|
||
בס״ד
|
||
|
||
שנת חמשת אלפים שש מאות וחמישים ושש לבריאת עולם
|
||
עשרים ושלשה לחודש אלול
|
||
במשהד
|
||
|
||
החתן משה בן משיאח
|
||
הכלה רבקה בת יעקב
|
||
|
||
[Isaiah 61:10 - visible in decorative header:]
|
||
שוש אשיש בה׳ תגל נפשי באלהי כי הלבישני בגדי ישע מעיל צדקה יעטני
|
||
כחתן יכהן פאר וככלה תעדה כליה
|
||
|
||
source_text_romanized: |
|
||
B'siyata d'shmaya (With Heaven's help)
|
||
|
||
In the year five thousand six hundred and fifty-six from the Creation of the world,
|
||
the twenty-third day of the month of Elul,
|
||
in Mashhad.
|
||
|
||
The groom: Mosheh son of Mashiah
|
||
The bride: Rivkah daughter of Ya'akov
|
||
|
||
[Isaiah 61:10 - decorative header blessing:]
|
||
"I will greatly rejoice in the LORD, my soul shall be joyful in my God.
|
||
For he has clothed me with the garments of salvation, he has covered me
|
||
with the robe of righteousness, as a bridegroom decks himself with a garland,
|
||
and as a bride adorns herself with her jewels."
|
||
|
||
expected_extraction:
|
||
description: "Hebrew ketubah extraction from REAL Mashhad, Iran document (1896)"
|
||
|
||
pico_observation:
|
||
observation_id: "ketubah_mashhad_5656_mosheh_rivkah"
|
||
observed_at: "2025-01-13T12:00:00Z"
|
||
source_type: "ketubah"
|
||
source_reference: "Ketubah, Mashhad, 23 Elul 5656 (September 1, 1896 CE), Yale Beinecke Hebrew MSS suppl 194"
|
||
archive: "Yale University, Beinecke Rare Book & Manuscript Library"
|
||
|
||
persons:
|
||
- person_index: 0
|
||
pnv_name:
|
||
literalName: "משה בן משיאח"
|
||
literalName_romanized: "Mosheh ben Mashiah"
|
||
givenName: "משה"
|
||
givenName_romanized: "Mosheh"
|
||
patronym: "משיאח"
|
||
patronym_romanized: "Mashiah"
|
||
roles:
|
||
- role_title: "חתן"
|
||
role_title_romanized: "chatan"
|
||
role_in_source: "groom"
|
||
biographical:
|
||
sex: "male"
|
||
religion: "Jewish"
|
||
community: "Mashhad Jewish community (Mashhadis)"
|
||
family_relationships:
|
||
father:
|
||
- person_index: 1
|
||
target_name: "משיאח"
|
||
spouse:
|
||
- person_index: 2
|
||
target_name: "רבקה בת יעקב"
|
||
context: "Groom (חתן) - the bridegroom in the marriage contract"
|
||
|
||
- person_index: 1
|
||
pnv_name:
|
||
literalName: "משיאח"
|
||
literalName_romanized: "Mashiah"
|
||
givenName: "משיאח"
|
||
givenName_romanized: "Mashiah"
|
||
biographical:
|
||
sex: "male"
|
||
note: "Name meaning 'Messiah' - common Persian Jewish name"
|
||
family_relationships:
|
||
child:
|
||
- person_index: 0
|
||
target_name: "משה"
|
||
context: "Father of the groom (implicit from patronymic)"
|
||
|
||
- person_index: 2
|
||
pnv_name:
|
||
literalName: "רבקה בת יעקב"
|
||
literalName_romanized: "Rivkah bat Ya'akov"
|
||
givenName: "רבקה"
|
||
givenName_romanized: "Rivkah"
|
||
givenName_english: "Rebecca"
|
||
patronym: "יעקב"
|
||
patronym_romanized: "Ya'akov"
|
||
roles:
|
||
- role_title: "כלה"
|
||
role_title_romanized: "kallah"
|
||
role_in_source: "bride"
|
||
biographical:
|
||
sex: "female"
|
||
religion: "Jewish"
|
||
community: "Mashhad Jewish community (Mashhadis)"
|
||
family_relationships:
|
||
father:
|
||
- person_index: 3
|
||
target_name: "יעקב"
|
||
spouse:
|
||
- person_index: 0
|
||
target_name: "משה בן משיאח"
|
||
context: "Bride (כלה) - daughter of Ya'akov"
|
||
|
||
- person_index: 3
|
||
pnv_name:
|
||
literalName: "יעקב"
|
||
literalName_romanized: "Ya'akov"
|
||
givenName: "יעקב"
|
||
givenName_romanized: "Ya'akov"
|
||
givenName_english: "Jacob"
|
||
biographical:
|
||
sex: "male"
|
||
note: "Biblical patriarch name - common in Jewish communities"
|
||
family_relationships:
|
||
child:
|
||
- person_index: 2
|
||
target_name: "רבקה"
|
||
context: "Father of the bride (implicit from patronymic)"
|
||
|
||
temporal_references:
|
||
- expression: "עשרים ושלשה לחודש אלול שנת חמשת אלפים שש מאות וחמישים ושש לבריאת עולם"
|
||
expression_romanized: "23rd day of the month of Elul, year 5656 from Creation"
|
||
normalized_gregorian: "1896-09-01"
|
||
calendar: "Hebrew"
|
||
type: "DATE"
|
||
components:
|
||
day: 23
|
||
month: "אלול (Elul)"
|
||
month_number: 6
|
||
year_hebrew: 5656
|
||
year_gregorian: 1896
|
||
era: "לבריאת עולם (from Creation)"
|
||
notes: "Elul is the 6th month of the civil year, 12th of the ecclesiastical year"
|
||
|
||
locations_mentioned:
|
||
- name: "משהד"
|
||
name_romanized: "Mashhad"
|
||
name_persian: "مشهد"
|
||
type: "city"
|
||
country: "Iran (then Qajar Persia)"
|
||
modern_country: "Iran"
|
||
coordinates: "36.2972, 59.6067"
|
||
historical_context: |
|
||
Mashhad is a major city in northeastern Iran, holy city of Shia Islam
|
||
(shrine of Imam Reza). The Jewish community dated to ancient times but
|
||
faced forced conversion in 1839. By 1896, some families openly practiced
|
||
Judaism while others remained crypto-Jews.
|
||
|
||
physical_description:
|
||
dimensions: "53 x 37 cm"
|
||
material: "ink and paint on paper"
|
||
decoration: |
|
||
- Red and green rules divide the paper into rectangular sections
|
||
- Middle section contains the ketubah text
|
||
- Top and sides filled with elaborate arch and floral patterns
|
||
- Colors: blue, gold, and silver paint
|
||
- Strips of red paper pasted on all four sides as frame
|
||
condition: "Some damage to the text containing the Isaiah quote and to the borders"
|
||
script: "Hebrew square script"
|
||
|
||
hebrew_naming_notes: |
|
||
Hebrew/Jewish naming conventions demonstrated in this REAL document:
|
||
|
||
1. PATRONYMIC SYSTEM:
|
||
- בן (ben): "son of" - used for males
|
||
- בת (bat): "daughter of" - used for females
|
||
- Example: משה בן משיאח = "Mosheh son of Mashiah"
|
||
|
||
2. PERSIAN JEWISH NAMES:
|
||
- משיאח (Mashiah/Messiah): Common Persian Jewish given name
|
||
- רבקה (Rivkah/Rebecca): Biblical matriarch name
|
||
- יעקב (Ya'akov/Jacob): Biblical patriarch name
|
||
|
||
3. KETUBAH STRUCTURE:
|
||
- Opening: בס״ד (B'siyata d'Shmaya - With Heaven's help)
|
||
- Date: Hebrew calendar from Creation (anno mundi)
|
||
- Location: City name in Hebrew transliteration
|
||
- Parties: Groom (חתן) and Bride (כלה) with patronymics
|
||
- Blessing: Often biblical verses (here Isaiah 61:10)
|
||
|
||
4. MASHHAD JEWISH CONTEXT:
|
||
- Community known as "Mashhadis" or "Jadid al-Islam"
|
||
- After 1839 pogrom, many practiced Judaism secretly
|
||
- Unique artistic traditions in ketubah decoration
|
||
- Persian influences in ornamentation style
|
||
|
||
provenance:
|
||
data_status: "REAL_HISTORICAL_DATA"
|
||
archive: "Yale University, Beinecke Rare Book & Manuscript Library"
|
||
collection: "Hebrew Manuscripts Supplement"
|
||
call_number: "Hebrew MSS suppl 194 (Broadside)"
|
||
catalog_record: "8574921"
|
||
object_id: "2067542"
|
||
digital_url: "https://digital.library.yale.edu/catalog/2067542"
|
||
iiif_manifest: "https://digital.library.yale.edu/manifests/2067542"
|
||
pdf_url: "https://digital.library.yale.edu/pdfs/2067542.pdf"
|
||
|
||
document_date_hebrew: "23 Elul 5656"
|
||
document_date_gregorian: "1896-09-01"
|
||
document_place: "Mashhad, Iran"
|
||
|
||
contributors:
|
||
groom: "Mosheh ben Mashiah"
|
||
bride: "Rivkah bat Ya'akov"
|
||
|
||
physical_extent: "1 leaf, 53 x 37 cm, color illustrations"
|
||
languages:
|
||
- "Hebrew"
|
||
- "Official Aramaic (700-300 BCE); Imperial Aramaic (700-300 BCE)"
|
||
|
||
subjects:
|
||
geographic: "Mashhad (Iran) -- Religious life and customs"
|
||
topical:
|
||
- "Ketubah -- Iran -- Mashhad"
|
||
- "Prenuptial agreements (Jewish law)"
|
||
|
||
genres:
|
||
- "Autographs"
|
||
- "Illustrations"
|
||
- "Ketubahs"
|
||
- "Manuscripts"
|
||
- "Marginalia"
|
||
|
||
rights: |
|
||
The use of this image may be subject to the copyright law of the
|
||
United States (Title 17, United States Code) or to site license or
|
||
other rights management terms and conditions. The person using the
|
||
image is liable for any infringement.
|
||
|
||
access_date: "2025-01-13"
|
||
|
||
citation: |
|
||
"Ketubah : Mashhad, Iran, 1896, September 1," Yale University Library,
|
||
Beinecke Rare Book and Manuscript Library, Hebrew MSS suppl 194 (Broadside),
|
||
Object ID 2067542. Digital Collections, https://digital.library.yale.edu/catalog/2067542
|
||
(accessed January 13, 2025).
|
||
|
||
verification_notes: |
|
||
This is a REAL historical document with verified provenance:
|
||
- Held at Yale University Beinecke Rare Book & Manuscript Library
|
||
- Fully digitized and publicly accessible
|
||
- Catalog record #8574921 with complete metadata
|
||
- Both principal parties (groom and bride) are named in Yale's catalog
|
||
- Physical dimensions and condition documented
|
||
- High-resolution images available via IIIF manifest
|
||
- Document represents unique Mashhad Jewish community traditions
|
||
|
||
# =============================================================================
|
||
# EXAMPLE 7: Spanish Colonial Baptism Record
|
||
# =============================================================================
|
||
# Source type: Libro de bautismos (Baptismal register)
|
||
# Language: Spanish
|
||
# Date: 1742
|
||
# Location: Mexico City, New Spain
|
||
# =============================================================================
|
||
|
||
example_7_spanish_colonial_baptism:
|
||
description: |
|
||
Spanish colonial baptismal records from New Spain (Mexico) include rich
|
||
genealogical data with casta (racial/social classification) designations
|
||
and compadrazgo (godparent) relationships. These records are invaluable
|
||
for tracing both family lineages and social networks.
|
||
|
||
Key features:
|
||
- Casta designations (español, mestizo, mulato, indio, etc.)
|
||
- Legitimacy markers (hijo legítimo vs hijo natural)
|
||
- Compadrazgo (godparent relationships)
|
||
- Place of origin (vecino de, natural de)
|
||
- Ecclesiastical formulae
|
||
|
||
source_text: |
|
||
En la ciudad de México, a veinte y tres días del mes de febrero de mil
|
||
setecientos cuarenta y dos años, yo el Br. Don Antonio de Mendoza,
|
||
teniente de cura de esta santa iglesia catedral, bauticé solemnemente,
|
||
puse óleo y crisma a Juan José, español, hijo legítimo de Don Pedro
|
||
García de la Cruz, español, natural de la villa de Puebla de los Ángeles,
|
||
y de Doña María Josefa de los Reyes, española, natural de esta ciudad.
|
||
|
||
Fueron sus padrinos Don Francisco Xavier de Castañeda, español, vecino
|
||
de esta ciudad, y Doña Ana María de la Encarnación, su legítima esposa,
|
||
a quienes advertí el parentesco espiritual y obligaciones que contrajeron.
|
||
|
||
Y lo firmé.
|
||
Br. Don Antonio de Mendoza
|
||
|
||
expected_extraction:
|
||
description: "Spanish colonial baptism demonstrating casta system and compadrazgo"
|
||
|
||
pico_observation:
|
||
observation_id: "bautismo_mexico_1742_juan_jose_garcia"
|
||
observed_at: "2025-12-12T12:00:00Z"
|
||
source_type: "baptismal_register"
|
||
source_reference: "Libro de Bautismos, Catedral de México, 23 Feb 1742"
|
||
|
||
persons:
|
||
- person_index: 0
|
||
pnv_name:
|
||
literalName: "Juan José"
|
||
givenName: "Juan José"
|
||
roles:
|
||
- role_title: "bautizado"
|
||
role_in_source: "baptized"
|
||
biographical:
|
||
casta: "español"
|
||
legitimacy: "hijo legítimo"
|
||
religion: "Catholic"
|
||
family_relationships:
|
||
parent:
|
||
- person_index: 1
|
||
target_name: "Don Pedro García de la Cruz"
|
||
- person_index: 2
|
||
target_name: "Doña María Josefa de los Reyes"
|
||
godparent:
|
||
- person_index: 3
|
||
target_name: "Don Francisco Xavier de Castañeda"
|
||
- person_index: 4
|
||
target_name: "Doña Ana María de la Encarnación"
|
||
context: "Infant being baptized"
|
||
|
||
- person_index: 1
|
||
pnv_name:
|
||
literalName: "Don Pedro García de la Cruz"
|
||
givenName: "Pedro"
|
||
surnamePrefix: "García de"
|
||
baseSurname: "la Cruz"
|
||
honorificPrefix: "Don"
|
||
biographical:
|
||
casta: "español"
|
||
origin: "natural de la villa de Puebla de los Ángeles"
|
||
family_relationships:
|
||
spouse:
|
||
- person_index: 2
|
||
target_name: "Doña María Josefa de los Reyes"
|
||
children:
|
||
- person_index: 0
|
||
target_name: "Juan José"
|
||
context: "Father of the baptized child"
|
||
|
||
- person_index: 2
|
||
pnv_name:
|
||
literalName: "Doña María Josefa de los Reyes"
|
||
givenName: "María Josefa"
|
||
surnamePrefix: "de"
|
||
baseSurname: "los Reyes"
|
||
honorificPrefix: "Doña"
|
||
biographical:
|
||
casta: "española"
|
||
origin: "natural de esta ciudad"
|
||
family_relationships:
|
||
spouse:
|
||
- person_index: 1
|
||
target_name: "Don Pedro García de la Cruz"
|
||
children:
|
||
- person_index: 0
|
||
target_name: "Juan José"
|
||
context: "Mother of the baptized child"
|
||
|
||
- person_index: 3
|
||
pnv_name:
|
||
literalName: "Don Francisco Xavier de Castañeda"
|
||
givenName: "Francisco Xavier"
|
||
surnamePrefix: "de"
|
||
baseSurname: "Castañeda"
|
||
honorificPrefix: "Don"
|
||
roles:
|
||
- role_title: "padrino"
|
||
role_in_source: "godfather"
|
||
biographical:
|
||
casta: "español"
|
||
residence: "vecino de esta ciudad"
|
||
family_relationships:
|
||
spouse:
|
||
- person_index: 4
|
||
target_name: "Doña Ana María de la Encarnación"
|
||
godchildren:
|
||
- person_index: 0
|
||
target_name: "Juan José"
|
||
compadre:
|
||
- person_index: 1
|
||
target_name: "Don Pedro García de la Cruz"
|
||
context: "Godfather (padrino)"
|
||
|
||
- person_index: 4
|
||
pnv_name:
|
||
literalName: "Doña Ana María de la Encarnación"
|
||
givenName: "Ana María"
|
||
surnamePrefix: "de"
|
||
baseSurname: "la Encarnación"
|
||
honorificPrefix: "Doña"
|
||
roles:
|
||
- role_title: "madrina"
|
||
role_in_source: "godmother"
|
||
biographical:
|
||
marital_status: "legítima esposa"
|
||
family_relationships:
|
||
spouse:
|
||
- person_index: 3
|
||
target_name: "Don Francisco Xavier de Castañeda"
|
||
godchildren:
|
||
- person_index: 0
|
||
target_name: "Juan José"
|
||
comadre:
|
||
- person_index: 2
|
||
target_name: "Doña María Josefa de los Reyes"
|
||
context: "Godmother (madrina)"
|
||
|
||
- person_index: 5
|
||
pnv_name:
|
||
literalName: "Br. Don Antonio de Mendoza"
|
||
givenName: "Antonio"
|
||
surnamePrefix: "de"
|
||
baseSurname: "Mendoza"
|
||
honorificPrefix: "Br. Don"
|
||
roles:
|
||
- role_title: "teniente de cura"
|
||
role_in_source: "officiant"
|
||
biographical:
|
||
ecclesiastical_position: "teniente de cura de esta santa iglesia catedral"
|
||
family_relationships: {}
|
||
context: "Priest who performed the baptism"
|
||
|
||
temporal_references:
|
||
- expression: "a veinte y tres días del mes de febrero de mil setecientos cuarenta y dos años"
|
||
normalized: "1742-02-23"
|
||
calendar: "Gregorian"
|
||
type: "DATE"
|
||
|
||
locations_mentioned:
|
||
- name: "ciudad de México"
|
||
type: "city"
|
||
administrative_entity: "New Spain"
|
||
- name: "santa iglesia catedral"
|
||
type: "church"
|
||
full_name: "Catedral Metropolitana de la Asunción de la Santísima Virgen María"
|
||
- name: "villa de Puebla de los Ángeles"
|
||
type: "city"
|
||
modern_name: "Puebla"
|
||
administrative_entity: "New Spain"
|
||
|
||
colonial_naming_notes: |
|
||
Spanish colonial naming conventions demonstrated:
|
||
- Don/Doña: honorific indicating Spanish (peninsular or criollo) status
|
||
- Br. (Bachiller): academic degree, often for clergy
|
||
- Casta system: español, mestizo, mulato, indio, etc.
|
||
- "natural de": indicates place of birth
|
||
- "vecino de": indicates place of residence
|
||
- "hijo legítimo": legitimate child (parents married)
|
||
- "hijo natural": illegitimate child (parents not married)
|
||
- Compadrazgo: godparent relationship creating spiritual kinship
|
||
- Padrino/madrina: godfather/godmother
|
||
- Compadre/comadre: relationship between godparents and parents
|
||
- "parentesco espiritual": spiritual kinship with religious obligations
|
||
|
||
provenance:
|
||
data_status: "SYNTHETIC_EXAMPLE"
|
||
notes: |
|
||
This example uses synthetic data based on standard Spanish colonial
|
||
baptismal formulae for demonstration purposes. Names, dates, and
|
||
locations are fictional but follow authentic 17th-century patterns.
|
||
For real examples, see PROVENANCE_SOURCES.md.
|
||
|
||
related_real_sources:
|
||
- archive: "Brigham Young University"
|
||
collection: "Script Tutorial - Spanish Colonial Baptisms"
|
||
digital_url: "https://script.byu.edu/spanish-handwriting/documents/church-records/baptisms"
|
||
document_type: "Tutorial with real transcription examples"
|
||
license: "Educational use"
|
||
|
||
- archive: "FamilySearch"
|
||
collection: "Mexico, Yucatán, Catholic Church Records, 1543-1977"
|
||
collection_id: "1909116"
|
||
digital_url: "https://www.familysearch.org/en/search/collection/1909116"
|
||
document_type: "Baptisms, marriages, deaths"
|
||
license: "Free with registration"
|
||
notes: "Contains some of earliest New World records (from 1543)"
|
||
|
||
- archive: "Archivo General de la Nación (AGN)"
|
||
location: "Mexico City, Mexico"
|
||
collection: "Colonial parish records"
|
||
document_type: "Spanish colonial baptismal records"
|
||
period: "16th-20th century CE"
|
||
languages: "Spanish, Nahuatl, Latin"
|
||
|
||
# =============================================================================
|
||
# EXAMPLE 8: Italian Notarial Act (1654 CE, Venice)
|
||
# =============================================================================
|
||
#
|
||
# Demonstrates extraction from an Italian notarial act showing:
|
||
# - Italian naming conventions (patronymic "fu", "quondam")
|
||
# - Venetian nobility titles (Nobil Homo, Magnifico)
|
||
# - Profession-based surnames (Fabbro, Ferrari)
|
||
# - Parish-based location (contrada, sestiere)
|
||
# - Compare/comare (godparent equivalents in civil context)
|
||
# =============================================================================
|
||
|
||
extraction_examples:
|
||
- example_id: "italian_notarial_act"
|
||
source_language: "Italian"
|
||
source_script: "Latin"
|
||
source_period: "1654 CE"
|
||
source_type: "notarial_act"
|
||
|
||
source_text: |
|
||
Adì 15 Marzo 1654, in Venetia.
|
||
|
||
Presenti: Il Nobil Homo Messer Giovanni Battista Morosini fu
|
||
quondam Magnifico Messer Andrea, della contrada di San Marco,
|
||
et sua moglie la Nobil Donna Madonna Caterina Contarini fu
|
||
quondam Messer Francesco. Testimoni: Messer Pietro fu Paolo
|
||
Fabbro, habitante nella contrada di San Polo, et Messer Marco
|
||
Antonio Ferrari fu Giovanni, bottegaio in Rialto. Rogato io
|
||
Notaro Antonio Zen fu quondam Messer Giacomo, Notaro publico
|
||
di Venetia.
|
||
|
||
expected_output:
|
||
pico_observation:
|
||
observation_id: "notarial_venice_1654-03-15_morosini"
|
||
source_type: "notarial_act"
|
||
source_reference: "Notarial act, Venice, March 15, 1654"
|
||
|
||
persons:
|
||
- person_index: 0
|
||
pnv_name:
|
||
literalName: "Il Nobil Homo Messer Giovanni Battista Morosini"
|
||
givenName: "Giovanni Battista"
|
||
baseSurname: "Morosini"
|
||
honorificPrefix: "Il Nobil Homo Messer"
|
||
roles:
|
||
- role_title: "principal party"
|
||
role_in_source: "party to act"
|
||
biographical:
|
||
social_status: "Venetian nobility"
|
||
patronymic: "fu quondam Magnifico Messer Andrea"
|
||
father_status: "deceased (quondam)"
|
||
family_relationships:
|
||
father:
|
||
- person_index: 1
|
||
target_name: "Magnifico Messer Andrea Morosini"
|
||
spouse:
|
||
- person_index: 2
|
||
target_name: "Nobil Donna Madonna Caterina Contarini"
|
||
context: "Principal party, Venetian noble"
|
||
|
||
- person_index: 1
|
||
pnv_name:
|
||
literalName: "Magnifico Messer Andrea Morosini"
|
||
givenName: "Andrea"
|
||
baseSurname: "Morosini"
|
||
honorificPrefix: "Magnifico Messer"
|
||
roles: []
|
||
biographical:
|
||
social_status: "Venetian nobility"
|
||
deceased: true
|
||
deceased_marker: "quondam"
|
||
family_relationships:
|
||
child:
|
||
- person_index: 0
|
||
target_name: "Giovanni Battista Morosini"
|
||
context: "Father of Giovanni Battista, deceased"
|
||
|
||
- person_index: 2
|
||
pnv_name:
|
||
literalName: "Nobil Donna Madonna Caterina Contarini"
|
||
givenName: "Caterina"
|
||
baseSurname: "Contarini"
|
||
honorificPrefix: "Nobil Donna Madonna"
|
||
roles:
|
||
- role_title: "moglie"
|
||
role_in_source: "wife"
|
||
biographical:
|
||
social_status: "Venetian nobility"
|
||
patronymic: "fu quondam Messer Francesco"
|
||
family_relationships:
|
||
father:
|
||
- person_index: 3
|
||
target_name: "Messer Francesco Contarini"
|
||
spouse:
|
||
- person_index: 0
|
||
target_name: "Giovanni Battista Morosini"
|
||
context: "Wife of Giovanni Battista"
|
||
|
||
- person_index: 3
|
||
pnv_name:
|
||
literalName: "Messer Francesco Contarini"
|
||
givenName: "Francesco"
|
||
baseSurname: "Contarini"
|
||
honorificPrefix: "Messer"
|
||
roles: []
|
||
biographical:
|
||
deceased: true
|
||
deceased_marker: "quondam"
|
||
family_relationships:
|
||
child:
|
||
- person_index: 2
|
||
target_name: "Caterina Contarini"
|
||
context: "Father of Caterina, deceased"
|
||
|
||
- person_index: 4
|
||
pnv_name:
|
||
literalName: "Messer Pietro fu Paolo Fabbro"
|
||
givenName: "Pietro"
|
||
baseSurname: "Fabbro"
|
||
honorificPrefix: "Messer"
|
||
roles:
|
||
- role_title: "testimone"
|
||
role_in_source: "witness"
|
||
biographical:
|
||
patronymic: "fu Paolo"
|
||
residence: "contrada di San Polo"
|
||
family_relationships:
|
||
father:
|
||
- person_index: 5
|
||
target_name: "Paolo Fabbro"
|
||
context: "First witness"
|
||
|
||
- person_index: 5
|
||
pnv_name:
|
||
literalName: "Paolo Fabbro"
|
||
givenName: "Paolo"
|
||
baseSurname: "Fabbro"
|
||
roles: []
|
||
biographical:
|
||
deceased: true
|
||
family_relationships:
|
||
child:
|
||
- person_index: 4
|
||
target_name: "Pietro Fabbro"
|
||
context: "Father of witness Pietro, deceased"
|
||
|
||
- person_index: 6
|
||
pnv_name:
|
||
literalName: "Messer Marco Antonio Ferrari fu Giovanni"
|
||
givenName: "Marco Antonio"
|
||
baseSurname: "Ferrari"
|
||
honorificPrefix: "Messer"
|
||
roles:
|
||
- role_title: "testimone"
|
||
role_in_source: "witness"
|
||
biographical:
|
||
patronymic: "fu Giovanni"
|
||
occupation: "bottegaio"
|
||
workplace: "Rialto"
|
||
family_relationships:
|
||
father:
|
||
- person_index: 7
|
||
target_name: "Giovanni Ferrari"
|
||
context: "Second witness, shopkeeper"
|
||
|
||
- person_index: 7
|
||
pnv_name:
|
||
literalName: "Giovanni Ferrari"
|
||
givenName: "Giovanni"
|
||
baseSurname: "Ferrari"
|
||
roles: []
|
||
biographical:
|
||
deceased: true
|
||
family_relationships:
|
||
child:
|
||
- person_index: 6
|
||
target_name: "Marco Antonio Ferrari"
|
||
context: "Father of witness Marco Antonio, deceased"
|
||
|
||
- person_index: 8
|
||
pnv_name:
|
||
literalName: "Notaro Antonio Zen fu quondam Messer Giacomo"
|
||
givenName: "Antonio"
|
||
baseSurname: "Zen"
|
||
honorificPrefix: "Notaro"
|
||
roles:
|
||
- role_title: "notaro"
|
||
role_in_source: "notary"
|
||
biographical:
|
||
patronymic: "fu quondam Messer Giacomo"
|
||
occupation: "Notaro publico di Venetia"
|
||
family_relationships:
|
||
father:
|
||
- person_index: 9
|
||
target_name: "Messer Giacomo Zen"
|
||
context: "Notary who drafted the act"
|
||
|
||
- person_index: 9
|
||
pnv_name:
|
||
literalName: "Messer Giacomo Zen"
|
||
givenName: "Giacomo"
|
||
baseSurname: "Zen"
|
||
honorificPrefix: "Messer"
|
||
roles: []
|
||
biographical:
|
||
deceased: true
|
||
deceased_marker: "quondam"
|
||
family_relationships:
|
||
child:
|
||
- person_index: 8
|
||
target_name: "Antonio Zen"
|
||
context: "Father of notary, deceased"
|
||
|
||
temporal_references:
|
||
- expression: "Adì 15 Marzo 1654"
|
||
normalized: "1654-03-15"
|
||
calendar: "Gregorian"
|
||
type: "DATE"
|
||
|
||
locations_mentioned:
|
||
- name: "Venetia"
|
||
name_modern: "Venice"
|
||
type: "city"
|
||
- name: "contrada di San Marco"
|
||
type: "parish/district"
|
||
parent: "Venice"
|
||
- name: "contrada di San Polo"
|
||
type: "parish/district"
|
||
parent: "Venice"
|
||
- name: "Rialto"
|
||
type: "district/market"
|
||
parent: "Venice"
|
||
|
||
italian_naming_notes: |
|
||
Italian notarial naming conventions demonstrated:
|
||
- "fu" / "quondam": indicates deceased father (Latin survival)
|
||
- "Magnifico Messer": high honorific for nobility
|
||
- "Nobil Homo" / "Nobil Donna": Venetian noble titles
|
||
- "Madonna": honorific for married noble women
|
||
- Profession surnames: Fabbro (smith), Ferrari (ironworker)
|
||
- "habitante in/nella": residence indicator
|
||
- "bottegaio": shopkeeper
|
||
- Venetian patronato system reflected in naming
|
||
- Contrada: parish neighborhood system of Venice
|
||
|
||
provenance:
|
||
data_status: "SYNTHETIC_EXAMPLE"
|
||
notes: |
|
||
This example uses synthetic data based on authentic 17th-century
|
||
Venetian notarial document formulae for demonstration purposes.
|
||
Names, dates, and locations are fictional but follow period-accurate
|
||
conventions. For real examples, see PROVENANCE_SOURCES.md.
|
||
|
||
related_real_sources:
|
||
- archive: "Italian Ministry of Culture"
|
||
project: "Antenati (Ancestors)"
|
||
digital_url: "https://antenati.cultura.gov.it/"
|
||
venice_url: "https://antenati.cultura.gov.it/archivio/state-archives-of-venezia/?lang=en"
|
||
document_type: "Civil registry, notarial acts, parish records"
|
||
period: "15th century+"
|
||
license: "Open Access"
|
||
|
||
- archive: "University of California Libraries"
|
||
collection: "Italian Notarial Documents Collection"
|
||
finding_aid: "https://oac.cdlib.org/findaid/ark:%2F13030%2Fc8v412zd"
|
||
document_count: "168 documents"
|
||
period: "1465-1635 CE"
|
||
locations: "Venice, Padua, Verona"
|
||
languages: "Latin, Italian (Venetian)"
|
||
|
||
- project: "SION-Digit (Sources for the History of Italian Jewish Notarial Documents)"
|
||
coverage: "Venice, Bordeaux, Amsterdam"
|
||
period: "16th-18th century CE"
|
||
focus: "Jewish community notarial acts"
|
||
languages: "Italian, Hebrew, Ladino"
|
||
|
||
# =============================================================================
|
||
# EXAMPLE 9: Greek Orthodox Parish Register (1875 CE, Thessaloniki)
|
||
# =============================================================================
|
||
#
|
||
# Demonstrates extraction from a Greek Orthodox baptismal register showing:
|
||
# - Greek script with romanization
|
||
# - Greek patronymics (του + genitive)
|
||
# - Godparent system (νονός/νονά)
|
||
# - Orthodox naming conventions
|
||
# - Deceased marker (μακαρίτης/μακαρίτισσα)
|
||
# =============================================================================
|
||
|
||
- example_id: "greek_baptismal_register"
|
||
source_language: "Greek"
|
||
source_script: "Greek"
|
||
source_period: "1875 CE"
|
||
source_type: "baptismal_register"
|
||
|
||
source_text: |
|
||
Ἐν Θεσσαλονίκῃ, τῇ δεκάτῃ πέμπτῃ Μαρτίου τοῦ ἔτους 1875.
|
||
|
||
Ἐβαπτίσθη ὁ Δημήτριος, υἱὸς τοῦ Νικολάου Παπαδοπούλου,
|
||
ἐμπόρου, καὶ τῆς νομίμου αὐτοῦ συζύγου Ἑλένης τῆς τοῦ
|
||
μακαρίτου Γεωργίου Οἰκονόμου. Νονὸς ὁ Κωνσταντῖνος
|
||
Καρατζᾶς τοῦ Ἰωάννου, ἰατρός. Ἱερεύς: ὁ Πρωτοπρεσβύτερος
|
||
Ἀθανάσιος Χρυσοστόμου.
|
||
|
||
expected_output:
|
||
pico_observation:
|
||
observation_id: "baptism_thessaloniki_1875-03-15_papadopoulos"
|
||
source_type: "baptismal_register"
|
||
source_reference: "Greek Orthodox baptismal register, Thessaloniki, March 15, 1875"
|
||
|
||
persons:
|
||
- person_index: 0
|
||
pnv_name:
|
||
literalName: "Δημήτριος"
|
||
literalName_romanized: "Dimitrios"
|
||
givenName: "Δημήτριος"
|
||
givenName_romanized: "Dimitrios"
|
||
roles:
|
||
- role_title: "βαπτισθείς"
|
||
role_in_source: "baptized infant"
|
||
biographical:
|
||
sex: "male"
|
||
religion: "Greek Orthodox"
|
||
family_relationships:
|
||
father:
|
||
- person_index: 1
|
||
target_name: "Νικόλαος Παπαδόπουλος"
|
||
mother:
|
||
- person_index: 2
|
||
target_name: "Ἑλένη"
|
||
godfather:
|
||
- person_index: 4
|
||
target_name: "Κωνσταντῖνος Καρατζᾶς"
|
||
context: "Baptized infant"
|
||
|
||
- person_index: 1
|
||
pnv_name:
|
||
literalName: "Νικόλαος Παπαδόπουλος"
|
||
literalName_romanized: "Nikolaos Papadopoulos"
|
||
givenName: "Νικόλαος"
|
||
givenName_romanized: "Nikolaos"
|
||
baseSurname: "Παπαδόπουλος"
|
||
baseSurname_romanized: "Papadopoulos"
|
||
roles:
|
||
- role_title: "πατήρ"
|
||
role_in_source: "father"
|
||
biographical:
|
||
occupation: "ἔμπορος (merchant)"
|
||
family_relationships:
|
||
child:
|
||
- person_index: 0
|
||
target_name: "Δημήτριος"
|
||
spouse:
|
||
- person_index: 2
|
||
target_name: "Ἑλένη"
|
||
context: "Father of the baptized, merchant"
|
||
|
||
- person_index: 2
|
||
pnv_name:
|
||
literalName: "Ἑλένη τῆς τοῦ μακαρίτου Γεωργίου Οἰκονόμου"
|
||
literalName_romanized: "Eleni tis tou makaritou Georgiou Oikonomou"
|
||
givenName: "Ἑλένη"
|
||
givenName_romanized: "Eleni"
|
||
roles:
|
||
- role_title: "μήτηρ"
|
||
role_in_source: "mother"
|
||
biographical:
|
||
marital_status: "νομίμη σύζυγος (lawful wife)"
|
||
patronymic: "τῆς τοῦ μακαρίτου Γεωργίου Οἰκονόμου"
|
||
family_relationships:
|
||
father:
|
||
- person_index: 3
|
||
target_name: "Γεώργιος Οἰκονόμος"
|
||
child:
|
||
- person_index: 0
|
||
target_name: "Δημήτριος"
|
||
spouse:
|
||
- person_index: 1
|
||
target_name: "Νικόλαος Παπαδόπουλος"
|
||
context: "Mother of the baptized"
|
||
|
||
- person_index: 3
|
||
pnv_name:
|
||
literalName: "μακαρίτης Γεώργιος Οἰκονόμος"
|
||
literalName_romanized: "makaritis Georgios Oikonomos"
|
||
givenName: "Γεώργιος"
|
||
givenName_romanized: "Georgios"
|
||
baseSurname: "Οἰκονόμος"
|
||
baseSurname_romanized: "Oikonomos"
|
||
roles: []
|
||
biographical:
|
||
deceased: true
|
||
deceased_marker: "μακαρίτης"
|
||
family_relationships:
|
||
child:
|
||
- person_index: 2
|
||
target_name: "Ἑλένη"
|
||
context: "Maternal grandfather, deceased"
|
||
|
||
- person_index: 4
|
||
pnv_name:
|
||
literalName: "Κωνσταντῖνος Καρατζᾶς τοῦ Ἰωάννου"
|
||
literalName_romanized: "Konstantinos Karatzas tou Ioannou"
|
||
givenName: "Κωνσταντῖνος"
|
||
givenName_romanized: "Konstantinos"
|
||
baseSurname: "Καρατζᾶς"
|
||
baseSurname_romanized: "Karatzas"
|
||
roles:
|
||
- role_title: "νονός"
|
||
role_in_source: "godfather"
|
||
biographical:
|
||
occupation: "ἰατρός (physician)"
|
||
patronymic: "τοῦ Ἰωάννου"
|
||
family_relationships:
|
||
father:
|
||
- person_index: 5
|
||
target_name: "Ἰωάννης Καρατζᾶς"
|
||
godchild:
|
||
- person_index: 0
|
||
target_name: "Δημήτριος"
|
||
context: "Godfather, physician"
|
||
|
||
- person_index: 5
|
||
pnv_name:
|
||
literalName: "Ἰωάννης Καρατζᾶς"
|
||
literalName_romanized: "Ioannis Karatzas"
|
||
givenName: "Ἰωάννης"
|
||
givenName_romanized: "Ioannis"
|
||
baseSurname: "Καρατζᾶς"
|
||
baseSurname_romanized: "Karatzas"
|
||
roles: []
|
||
biographical: {}
|
||
family_relationships:
|
||
child:
|
||
- person_index: 4
|
||
target_name: "Κωνσταντῖνος Καρατζᾶς"
|
||
context: "Father of godfather"
|
||
|
||
- person_index: 6
|
||
pnv_name:
|
||
literalName: "Πρωτοπρεσβύτερος Ἀθανάσιος Χρυσοστόμου"
|
||
literalName_romanized: "Protopresbyteros Athanasios Chrysostomou"
|
||
givenName: "Ἀθανάσιος"
|
||
givenName_romanized: "Athanasios"
|
||
patronymic: "Χρυσοστόμου"
|
||
patronymic_romanized: "Chrysostomou"
|
||
honorificPrefix: "Πρωτοπρεσβύτερος"
|
||
roles:
|
||
- role_title: "ἱερεύς"
|
||
role_in_source: "priest"
|
||
biographical:
|
||
ecclesiastical_rank: "Πρωτοπρεσβύτερος (Protopresbyter/Archpriest)"
|
||
family_relationships: {}
|
||
context: "Officiating priest"
|
||
|
||
temporal_references:
|
||
- expression: "τῇ δεκάτῃ πέμπτῃ Μαρτίου τοῦ ἔτους 1875"
|
||
expression_romanized: "ti dekati pempti Martiou tou etous 1875"
|
||
normalized: "1875-03-15"
|
||
calendar: "Julian"
|
||
type: "DATE"
|
||
note: "Greek Orthodox used Julian calendar; Gregorian equivalent: March 27, 1875"
|
||
|
||
locations_mentioned:
|
||
- name: "Θεσσαλονίκη"
|
||
name_romanized: "Thessaloniki"
|
||
type: "city"
|
||
modern_country: "Greece"
|
||
historical_context: "Ottoman Empire (Selanik vilayet)"
|
||
|
||
greek_naming_notes: |
|
||
Greek Orthodox naming conventions demonstrated:
|
||
- "τοῦ" + genitive: patronymic marker ("son/daughter of")
|
||
- "μακαρίτης/μακαρίτισσα": deceased marker ("the late")
|
||
- "νομίμη σύζυγος": lawful wife
|
||
- "νονός/νονά": godfather/godmother
|
||
- Surnames from occupations: Παπαδόπουλος (priest's son), Οἰκονόμος (steward)
|
||
- Ecclesiastical titles: Πρωτοπρεσβύτερος (Archpriest)
|
||
- Polytonic Greek orthography common in 19th century
|
||
- Julian calendar used by Greek Orthodox Church
|
||
|
||
provenance:
|
||
data_status: "SYNTHETIC_EXAMPLE"
|
||
notes: |
|
||
This example uses synthetic data based on authentic Greek Orthodox
|
||
baptismal register formulae for demonstration purposes. Names, dates,
|
||
and locations are fictional but follow 19th-century conventions.
|
||
For real examples, see PROVENANCE_SOURCES.md.
|
||
|
||
related_real_sources:
|
||
- archive: "FamilySearch"
|
||
wiki_url: "https://www.familysearch.org/en/wiki/Greece_Church_Records"
|
||
document_type: "Baptisms, marriages, deaths"
|
||
period: "17th century - 1925 CE"
|
||
language: "Greek"
|
||
license: "Free with registration"
|
||
notes: "Greek Orthodox records are primary source before 1925 civil registration"
|
||
|
||
- archive: "Γενικά Αρχεία του Κράτους (General State Archives of Greece)"
|
||
abbreviation: "GAK"
|
||
document_type: "Church records, civil registry, Ottoman-era documents"
|
||
period: "15th century - present"
|
||
languages: "Greek, Ottoman Turkish"
|
||
notes: "National archive with records from all Greek regions"
|
||
|
||
- resource: "Greek Ancestry"
|
||
coverage: "Village church records guide"
|
||
document_type: "Baptismal registers, marriage registers"
|
||
notes: "Guides to accessing island and mainland records"
|
||
|
||
# =============================================================================
|
||
# EXAMPLE 10: Russian Imperial Metrical Book - Birth of Stefan Nowicki (1894)
|
||
# =============================================================================
|
||
#
|
||
# REAL HISTORICAL DATA from Archiwum Państwowe w Poznaniu
|
||
#
|
||
# Demonstrates extraction from a Russian Imperial metrical book showing:
|
||
# - Cyrillic script with romanization
|
||
# - Polish names recorded in Russian (Congress Poland context)
|
||
# - Pre-revolutionary orthography (ъ, ѣ)
|
||
# - Julian/Gregorian calendar dual dating
|
||
# - Восприемники (godparents/sponsors)
|
||
# - Village-level vital records
|
||
#
|
||
# Source: BYU Script Tutorial - fully transcribed with verification
|
||
# =============================================================================
|
||
|
||
- example_id: "russian_metrical_book_osiek_wielki_1894"
|
||
source_language: "Russian"
|
||
source_script: "Cyrillic (pre-1918 orthography)"
|
||
source_period: "1894 CE (Gregorian) / 1893 CE (Julian)"
|
||
source_type: "metrical_book"
|
||
document_subtype: "birth_record"
|
||
|
||
source_text: |
|
||
Любины
|
||
Состаялосъ въ деревнѣ осѣкъ велькій двадцать седьмаго Декабря
|
||
/:восьмаго Января:/ тысяча восемьсоть девяносто третяго (четвертаго) года
|
||
въ одинадцать часовъ утра Явился Янъ Новицкій /:Jan Nowicki:/
|
||
сорока лѣтъ отъ роду земледѣлецъ изъ Любинъ, въ присутствіи
|
||
Францишка Новицкаго сорока лѣтъ, и Михаила Влодарчика
|
||
шестидесяти лѣтъ отъ роду, обоихъ земледѣльцевъ изъ Любинъ
|
||
и предьявилъ намъ младенца мужскаго пола, объявляя
|
||
что онъ родился въ Любинахъ двадцать пятаго Декабря
|
||
/:шестаго Января:/ текущаго года, въ четыре часа вечеромъ
|
||
отъ законной его жены Маріанны изъ Адамковъ /:Mary-
|
||
anny z Adamkow:/ тридцати лѣтъ отъ роду, младенцу
|
||
этому при святомъ крещеніи совершенномъ сего
|
||
числа дано имя Стефанъ /:Stefan:/ а воспріемниками
|
||
его были Войцех Гаудынъ, и Катаржина Гембка.
|
||
Актъ сей объявляющему и свидѣтелямъ негра-
|
||
мотнымъ прочитанъ нами только подписанъ
|
||
Ксндзъ Павелъ Выборскій
|
||
|
||
source_text_romanized: |
|
||
Lyubiny
|
||
Sostoyalos' v derevne Osek Vel'kiy dvadtsat' sed'mago Dekabrya
|
||
/:vos'mago Yanvarya:/ tysyacha vosem'sot' devyanosto tret'yago (chetvertago) goda
|
||
v odinnadtsat' chasov utra Yavilsya Yan Novitskiy /:Jan Nowicki:/
|
||
soroka let ot rodu zemledelets iz Lyubin, v prisutstvii
|
||
Frantsishka Novitskago soroka let, i Mikhaila Vlodarchika
|
||
shestidesyati let ot rodu, oboikh zemledeltsev iz Lyubin
|
||
i pred'yavil nam mladentsa muzhskago pola, ob'yavlyaya
|
||
chto on rodilsya v Lyubinakh dvadtsat' pyatago Dekabrya
|
||
/:shestago Yanvarya:/ tekushchago goda, v chetyre chasa vecherom
|
||
ot zakonnoy ego zheny Marianny iz Adamkov /:Mary-
|
||
anny z Adamkow:/ tridtsati let ot rodu, mladentsu
|
||
etomu pri svyatom kreshchenii sovershennom sego
|
||
chisla dano imya Stefan /:Stefan:/ a vospriyemnikami
|
||
ego byli Voytsekh Gaudyn, i Katarzhina Gembka.
|
||
Akt sey ob'yavlyayushchemu i svidetel'yam negra-
|
||
motnym prochitan nami tol'ko podpisan
|
||
Ksndz Pavel Vyborskiy
|
||
|
||
source_text_english: |
|
||
Lubin
|
||
It happened in the village of Osiek Wielki on the twenty-seventh of December
|
||
/:eighth of January:/ in the year one thousand eight hundred ninety-three (four)
|
||
at eleven o'clock in the morning. Appeared Jan Nowicki /:Jan Nowicki:/
|
||
forty years of age, farmer from Lubin, in the presence of
|
||
Franciszek Nowicki, forty years old, and Michał Włodarczyk
|
||
sixty years of age, both farmers from Lubin
|
||
and presented to us an infant of the male sex, declaring
|
||
that he was born in Lubin on the twenty-fifth of December
|
||
/:sixth of January:/ of the current year, at four o'clock in the evening
|
||
of his lawful wife Marianna née Adamkow /:Mary-
|
||
anna z Adamkow:/ thirty years of age. To this infant,
|
||
at the holy baptism performed on this
|
||
date, was given the name Stefan /:Stefan:/ and his godparents
|
||
were Wojciech Gaudyn and Katarzyna Gembka.
|
||
This act, to the declarant and to the illiterate witnesses,
|
||
was read by us and only signed.
|
||
Priest Paweł Wyborski
|
||
|
||
expected_output:
|
||
pico_observation:
|
||
observation_id: "birth_osiek_wielki_1894_stefan_nowicki"
|
||
source_type: "metrical_book"
|
||
source_reference: "Akta stanu cywilnego Parafii Rzymskokatolickiej Osiek Wielki, Reference Code 54/792/0/6.1/140, scan 4/76"
|
||
archive: "Archiwum Państwowe w Poznaniu Oddział w Koninie"
|
||
|
||
persons:
|
||
- person_index: 0
|
||
pnv_name:
|
||
literalName: "Стефанъ Новицкій"
|
||
literalName_romanized: "Stefan Novitskiy"
|
||
literalName_polish: "Stefan Nowicki"
|
||
givenName: "Стефанъ"
|
||
givenName_romanized: "Stefan"
|
||
baseSurname: "Новицкій"
|
||
baseSurname_romanized: "Novitskiy"
|
||
baseSurname_polish: "Nowicki"
|
||
roles:
|
||
- role_title: "младенецъ"
|
||
role_in_source: "infant"
|
||
biographical:
|
||
sex: "male"
|
||
religion: "Roman Catholic"
|
||
birth_date_julian: "1893-12-25"
|
||
birth_date_gregorian: "1894-01-06"
|
||
baptism_date_julian: "1893-12-27"
|
||
baptism_date_gregorian: "1894-01-08"
|
||
birth_place: "Любины (Lubin)"
|
||
birth_time: "4 o'clock in the evening"
|
||
family_relationships:
|
||
father:
|
||
- person_index: 1
|
||
target_name: "Янъ Новицкій"
|
||
mother:
|
||
- person_index: 2
|
||
target_name: "Маріанна изъ Адамковъ"
|
||
godfather:
|
||
- person_index: 5
|
||
target_name: "Войцех Гаудынъ"
|
||
godmother:
|
||
- person_index: 6
|
||
target_name: "Катаржина Гембка"
|
||
context: "Newborn infant, subject of the birth registration"
|
||
|
||
- person_index: 1
|
||
pnv_name:
|
||
literalName: "Янъ Новицкій"
|
||
literalName_romanized: "Yan Novitskiy"
|
||
literalName_polish: "Jan Nowicki"
|
||
givenName: "Янъ"
|
||
givenName_romanized: "Yan"
|
||
givenName_polish: "Jan"
|
||
baseSurname: "Новицкій"
|
||
baseSurname_romanized: "Novitskiy"
|
||
baseSurname_polish: "Nowicki"
|
||
roles:
|
||
- role_title: "отецъ"
|
||
role_in_source: "father"
|
||
- role_title: "объявляющій"
|
||
role_in_source: "declarant"
|
||
biographical:
|
||
sex: "male"
|
||
age: 40
|
||
age_expression: "сорока лѣтъ отъ роду"
|
||
occupation: "земледѣлецъ (farmer)"
|
||
residence: "Любины (Lubin)"
|
||
literacy: "illiterate (implied - act read to him)"
|
||
family_relationships:
|
||
child:
|
||
- person_index: 0
|
||
target_name: "Стефанъ Новицкій"
|
||
spouse:
|
||
- person_index: 2
|
||
target_name: "Маріанна изъ Адамковъ"
|
||
possible_relative:
|
||
- person_index: 3
|
||
target_name: "Францишекъ Новицкій"
|
||
relationship_type: "same surname - possibly brother or cousin"
|
||
context: "Father of the infant, farmer from Lubin, appeared to register the birth"
|
||
|
||
- person_index: 2
|
||
pnv_name:
|
||
literalName: "Маріанна изъ Адамковъ"
|
||
literalName_romanized: "Marianna iz Adamkov"
|
||
literalName_polish: "Maryanna z Adamkow"
|
||
givenName: "Маріанна"
|
||
givenName_romanized: "Marianna"
|
||
givenName_polish: "Maryanna"
|
||
maidenName: "Адамковъ"
|
||
maidenName_romanized: "Adamkov"
|
||
maidenName_polish: "Adamkow"
|
||
roles:
|
||
- role_title: "мать"
|
||
role_in_source: "mother"
|
||
biographical:
|
||
sex: "female"
|
||
age: 30
|
||
age_expression: "тридцати лѣтъ отъ роду"
|
||
marital_status: "законная жена (lawful wife)"
|
||
maiden_name_marker: "изъ (née/z)"
|
||
family_relationships:
|
||
child:
|
||
- person_index: 0
|
||
target_name: "Стефанъ Новицкій"
|
||
spouse:
|
||
- person_index: 1
|
||
target_name: "Янъ Новицкій"
|
||
context: "Mother of the infant, lawful wife of Jan Nowicki"
|
||
|
||
- person_index: 3
|
||
pnv_name:
|
||
literalName: "Францишекъ Новицкій"
|
||
literalName_romanized: "Frantsishek Novitskiy"
|
||
literalName_polish: "Franciszek Nowicki"
|
||
givenName: "Францишекъ"
|
||
givenName_romanized: "Frantsishek"
|
||
givenName_polish: "Franciszek"
|
||
baseSurname: "Новицкій"
|
||
baseSurname_romanized: "Novitskiy"
|
||
baseSurname_polish: "Nowicki"
|
||
roles:
|
||
- role_title: "свидѣтель"
|
||
role_in_source: "witness"
|
||
biographical:
|
||
sex: "male"
|
||
age: 40
|
||
age_expression: "сорока лѣтъ"
|
||
occupation: "земледѣлецъ (farmer)"
|
||
residence: "Любины (Lubin)"
|
||
literacy: "illiterate (неграмотный)"
|
||
family_relationships:
|
||
possible_relative:
|
||
- person_index: 1
|
||
target_name: "Янъ Новицкій"
|
||
relationship_type: "same surname, same age, same village - possibly brother"
|
||
context: "First witness, farmer from Lubin, same surname as father"
|
||
|
||
- person_index: 4
|
||
pnv_name:
|
||
literalName: "Михаилъ Влодарчикъ"
|
||
literalName_romanized: "Mikhail Vlodarchik"
|
||
literalName_polish: "Michał Włodarczyk"
|
||
givenName: "Михаилъ"
|
||
givenName_romanized: "Mikhail"
|
||
givenName_polish: "Michał"
|
||
baseSurname: "Влодарчикъ"
|
||
baseSurname_romanized: "Vlodarchik"
|
||
baseSurname_polish: "Włodarczyk"
|
||
roles:
|
||
- role_title: "свидѣтель"
|
||
role_in_source: "witness"
|
||
biographical:
|
||
sex: "male"
|
||
age: 60
|
||
age_expression: "шестидесяти лѣтъ отъ роду"
|
||
occupation: "земледѣлецъ (farmer)"
|
||
residence: "Любины (Lubin)"
|
||
literacy: "illiterate (неграмотный)"
|
||
family_relationships: {}
|
||
context: "Second witness, farmer from Lubin, age 60"
|
||
|
||
- person_index: 5
|
||
pnv_name:
|
||
literalName: "Войцех Гаудынъ"
|
||
literalName_romanized: "Voytsekh Gaudyn"
|
||
literalName_polish: "Wojciech Gaudyn"
|
||
givenName: "Войцех"
|
||
givenName_romanized: "Voytsekh"
|
||
givenName_polish: "Wojciech"
|
||
baseSurname: "Гаудынъ"
|
||
baseSurname_romanized: "Gaudyn"
|
||
baseSurname_polish: "Gaudyn"
|
||
roles:
|
||
- role_title: "воспріемникъ"
|
||
role_in_source: "godfather"
|
||
biographical:
|
||
sex: "male"
|
||
family_relationships:
|
||
godchild:
|
||
- person_index: 0
|
||
target_name: "Стефанъ Новицкій"
|
||
context: "Godfather (baptismal sponsor)"
|
||
|
||
- person_index: 6
|
||
pnv_name:
|
||
literalName: "Катаржина Гембка"
|
||
literalName_romanized: "Katarzhina Gembka"
|
||
literalName_polish: "Katarzyna Gembka"
|
||
givenName: "Катаржина"
|
||
givenName_romanized: "Katarzhina"
|
||
givenName_polish: "Katarzyna"
|
||
baseSurname: "Гембка"
|
||
baseSurname_romanized: "Gembka"
|
||
baseSurname_polish: "Gembka"
|
||
roles:
|
||
- role_title: "воспріемница"
|
||
role_in_source: "godmother"
|
||
biographical:
|
||
sex: "female"
|
||
family_relationships:
|
||
godchild:
|
||
- person_index: 0
|
||
target_name: "Стефанъ Новицкій"
|
||
context: "Godmother (baptismal sponsor)"
|
||
|
||
- person_index: 7
|
||
pnv_name:
|
||
literalName: "Ксндзъ Павелъ Выборскій"
|
||
literalName_romanized: "Ksndz Pavel Vyborskiy"
|
||
literalName_polish: "Ksiądz Paweł Wyborski"
|
||
givenName: "Павелъ"
|
||
givenName_romanized: "Pavel"
|
||
givenName_polish: "Paweł"
|
||
baseSurname: "Выборскій"
|
||
baseSurname_romanized: "Vyborskiy"
|
||
baseSurname_polish: "Wyborski"
|
||
honorificPrefix: "Ксндзъ (Priest)"
|
||
roles:
|
||
- role_title: "ксндзъ"
|
||
role_in_source: "priest"
|
||
- role_title: "registrar"
|
||
role_in_source: "signed the act"
|
||
biographical:
|
||
sex: "male"
|
||
ecclesiastical_status: "Roman Catholic priest"
|
||
literacy: "literate (only signer)"
|
||
family_relationships: {}
|
||
context: "Officiating priest who performed baptism and signed the registration"
|
||
|
||
temporal_references:
|
||
- expression: "тысяча восемьсоть девяносто третяго (четвертаго) года"
|
||
expression_romanized: "tysyacha vosem'sot' devyanosto tret'yago (chetvertago) goda"
|
||
normalized_julian: "1893"
|
||
normalized_gregorian: "1894"
|
||
calendar: "Dual (Julian/Gregorian)"
|
||
type: "YEAR"
|
||
note: "Document shows both Julian (1893) and Gregorian (1894) years"
|
||
- expression: "двадцать седьмаго Декабря /:восьмаго Января:/"
|
||
expression_romanized: "dvadtsat' sed'mago Dekabrya /:vos'mago Yanvarya:/"
|
||
normalized_julian: "1893-12-27"
|
||
normalized_gregorian: "1894-01-08"
|
||
calendar: "Dual (Julian/Gregorian)"
|
||
type: "DATE"
|
||
event: "registration and baptism"
|
||
- expression: "двадцать пятаго Декабря /:шестаго Января:/"
|
||
expression_romanized: "dvadtsat' pyatago Dekabrya /:shestago Yanvarya:/"
|
||
normalized_julian: "1893-12-25"
|
||
normalized_gregorian: "1894-01-06"
|
||
calendar: "Dual (Julian/Gregorian)"
|
||
type: "DATE"
|
||
event: "birth"
|
||
note: "Born on Christmas Day (Julian calendar)"
|
||
- expression: "въ четыре часа вечеромъ"
|
||
expression_romanized: "v chetyre chasa vecherom"
|
||
normalized: "16:00"
|
||
type: "TIME"
|
||
event: "birth"
|
||
- expression: "въ одинадцать часовъ утра"
|
||
expression_romanized: "v odinnadtsat' chasov utra"
|
||
normalized: "11:00"
|
||
type: "TIME"
|
||
event: "registration"
|
||
|
||
locations_mentioned:
|
||
- name: "Осѣкъ Велькій"
|
||
name_romanized: "Osek Vel'kiy"
|
||
name_polish: "Osiek Wielki"
|
||
type: "village (derevnya)"
|
||
modern_location: "Greater Poland Voivodeship, Poland"
|
||
coordinates: "52.2461, 18.6207"
|
||
geonames_url: "https://www.google.com/maps/place/Osiek+Wielki,+Poland"
|
||
- name: "Любины"
|
||
name_romanized: "Lyubiny"
|
||
name_polish: "Lubin"
|
||
type: "village"
|
||
note: "Village where the family resided and child was born"
|
||
- name: "Parafia Rzymskokatolicka Osiek Wielki"
|
||
type: "parish"
|
||
note: "Roman Catholic Parish of Osiek Wielki - registration authority"
|
||
|
||
russian_naming_notes: |
|
||
Congress Poland naming conventions demonstrated in this REAL document:
|
||
|
||
1. DUAL SCRIPT NOTATION:
|
||
- Polish names recorded in both Russian Cyrillic AND Latin script
|
||
- Example: "Янъ Новицкій /:Jan Nowicki:/"
|
||
- Slashes and colons mark the Latin/Polish original
|
||
|
||
2. PRE-REVOLUTIONARY ORTHOGRAPHY:
|
||
- Hard sign (ъ) at end of words: Новицкій, Стефанъ
|
||
- Yat (ѣ) instead of е: лѣтъ, деревнѣ, свидѣтелямъ
|
||
- -аго/-яго genitive endings (later simplified to -ого/-его)
|
||
|
||
3. POLISH MAIDEN NAME CONVENTION:
|
||
- "изъ Адамковъ" = "z Adamkow" = née Adamkow
|
||
- "изъ" (from) marks maiden/birth name
|
||
|
||
4. WITNESSES (свидѣтели):
|
||
- Two male witnesses required for registration
|
||
- Both noted as illiterate (неграмотнымъ)
|
||
- Father (declarant) also illiterate - act "read" to them
|
||
|
||
5. CALENDAR SYSTEM:
|
||
- Russian Empire used Julian calendar
|
||
- Congress Poland (under Russian rule) noted both dates
|
||
- 12-day difference in 1893-1894
|
||
- Format: Julian date /:Gregorian date:/
|
||
|
||
6. GODPARENTS (воспріемники):
|
||
- Male: воспріемникъ (godfather)
|
||
- Female: воспріемница (godmother)
|
||
- Not necessarily from same family as parents
|
||
|
||
7. SOCIAL/OCCUPATIONAL TERMS:
|
||
- земледѣлецъ = farmer/agriculturalist
|
||
- ксндзъ = ksiądz (Polish priest title, from German "Knez")
|
||
|
||
provenance:
|
||
data_status: "REAL_HISTORICAL_DATA"
|
||
archive: "Archiwum Państwowe w Poznaniu Oddział w Koninie"
|
||
archive_english: "State Archive in Poznań, Konin Branch"
|
||
collection: "Akta stanu cywilnego Parafii Rzymskokatolickiej Osiek Wielki (pow. kolski)"
|
||
collection_english: "Civil Registration Records of the Roman Catholic Parish of Osiek Wielki (Koło district)"
|
||
reference_code: "54/792/0/6.1/140"
|
||
scan_number: "4 of 76"
|
||
document_date_julian: "1893-12-27"
|
||
document_date_gregorian: "1894-01-08"
|
||
digital_url: "https://szukajwarchiwach.gov.pl"
|
||
tutorial_url: "https://script.byu.edu/russian-handwriting/transcription/birth/osiek-wielki-poland/1894"
|
||
license: "Public domain (historical document over 100 years old)"
|
||
|
||
citation: |
|
||
"Akta stanu cywilnego Parafii Rzymskokatolickiej Osiek Wielki (pow. kolski),"
|
||
Archiwum Państwowe w Poznaniu Oddział w Koninie, Szukaj w Archiwach
|
||
(szukajwarchiwach.gov.pl: accessed 25 January 2023), entry for Stefan Novitsky,
|
||
Catholic birth record, 6 January 1894 (Gregorian date), Osiek Wielki, Czołowo,
|
||
Koło, Kaliska, Russian Empire, Reference Code 54/792/0/6.1/140, scan no. 4 of 76.
|
||
|
||
transcription_source:
|
||
institution: "Brigham Young University"
|
||
project: "Script Tutorial"
|
||
url: "https://script.byu.edu/russian-handwriting/transcription/birth/osiek-wielki-poland/1894"
|
||
access_date: "2025-01-13"
|
||
notes: "Complete line-by-line transcription with Russian original, romanization, and English translation"
|
||
|
||
verification_notes: |
|
||
This is a REAL historical document with verified transcription:
|
||
- Original held at Polish State Archives (Archiwum Państwowe)
|
||
- Transcribed and verified by BYU Script Tutorial paleographers
|
||
- All 8 persons are real historical individuals
|
||
- Names provided in both Russian Cyrillic and Polish Latin script in original
|
||
- Stefan Nowicki born 6 January 1894 (Gregorian) in Lubin village
|
||
- Family: farmers (земледѣльцы) in Greater Poland region
|
||
- Document context: Congress Poland under Russian Imperial rule
|
||
|
||
# ---------------------------------------------------------------------------
|
||
# Example 11: Ottoman Turkish Sijill (Court Record)
|
||
# ---------------------------------------------------------------------------
|
||
# Period: 1258 AH (1842 CE)
|
||
# Source: Şer'iyye Sicili (Sharia Court Register), Demirciköy
|
||
# Language: Ottoman Turkish (Arabic script)
|
||
# Key features:
|
||
# - Honorific titles: Ağa, Efendi, Çelebi, Hatun
|
||
# - Patronymics: bin (son of), bint (daughter of)
|
||
# - Deceased markers: merhum/merhume (المرحوم/المرحومة)
|
||
# - Hijri calendar
|
||
# - Mixed Arabic-Turkish vocabulary
|
||
# - Court terminology: mahkeme, şahid, mübayi', ba'i
|
||
# ---------------------------------------------------------------------------
|
||
|
||
- example_id: "ottoman_sijill"
|
||
source_language: "Ottoman Turkish"
|
||
source_script: "Arabic"
|
||
source_period: "1258 AH (1842 CE)"
|
||
source_type: "sijill"
|
||
document_subtype: "property_sale"
|
||
archive_context: "Şer'iyye Sicilleri (Islamic Court Registers)"
|
||
|
||
source_text: |
|
||
بسم الله الرحمن الرحيم
|
||
|
||
مجلس شرع شريفده محمد آغا بن عبد الله مرحوم قصبه دميرجیکوی
|
||
ساکنلرندن محمد بن احمد افندی و زوجهسی فاطمه خاتون بنت علیاوغلو
|
||
حاضر اولوب محمد آغا طرفندن یکری بش غروش بدل معلوم ایله صاتیلدی
|
||
|
||
شهود الحال: حسن افندی بن عمر، ابراهیم چلبی بن مصطفی
|
||
|
||
فی اوائل شهر رجب سنة ١٢٥٨
|
||
|
||
source_text_romanized: |
|
||
Bismillahirrahmanirrahim
|
||
|
||
Meclis-i şer'-i şerifde Mehmed Ağa bin Abdullah merhum kasaba Demirciköy
|
||
sakinlerinden Mehmed bin Ahmed Efendi ve zevcesi Fatma Hatun bint Ali-oğlu
|
||
hazır olub Mehmed Ağa tarafından yirmi beş guruş bedel-i ma'lum ile satıldı
|
||
|
||
Şuhud al-hal: Hasan Efendi bin Ömer, İbrahim Çelebi bin Mustafa
|
||
|
||
Fi evail-i şehr-i Receb sene 1258
|
||
|
||
source_text_english: |
|
||
In the name of God, the Merciful, the Compassionate
|
||
|
||
In the noble Sharia court, Mehmed Ağa son of the late Abdullah, [sold to]
|
||
residents of the town of Demirciköy, Mehmed son of Ahmed Efendi and his
|
||
wife Fatma Hatun daughter of Ali-oğlu, who were present, for the known
|
||
price of twenty-five guruş, [the property] was sold by Mehmed Ağa.
|
||
|
||
Witnesses present: Hasan Efendi son of Ömer, İbrahim Çelebi son of Mustafa
|
||
|
||
In early Receb of the year 1258 [Hijri]
|
||
|
||
expected_output:
|
||
pico_observation:
|
||
observation_id: "sijill_demircikoy_1258ah_sale"
|
||
source_type: "sijill"
|
||
source_reference: "Şer'iyye Sicili, Demirciköy, Receb 1258 AH"
|
||
|
||
persons:
|
||
- person_index: 0
|
||
pnv_name:
|
||
literalName: "محمد آغا بن عبد الله"
|
||
literalName_romanized: "Mehmed Ağa bin Abdullah"
|
||
givenName: "محمد"
|
||
givenName_romanized: "Mehmed"
|
||
title: "آغا (Ağa)"
|
||
patronymic: "بن عبد الله"
|
||
patronymic_romanized: "bin Abdullah"
|
||
roles:
|
||
- role_title: "بائع (ba'i)"
|
||
role_in_source: "seller"
|
||
biographical:
|
||
sex: "male"
|
||
status: "deceased"
|
||
deceased_marker: "مرحوم (merhum)"
|
||
social_rank: "Ağa (military/landowning class)"
|
||
family_relationships:
|
||
father:
|
||
- name: "عبد الله (Abdullah)"
|
||
status: "deceased"
|
||
context: "Seller (deceased), Ağa = military/landowning"
|
||
|
||
- person_index: 1
|
||
pnv_name:
|
||
literalName: "محمد بن احمد افندی"
|
||
literalName_romanized: "Mehmed bin Ahmed Efendi"
|
||
givenName: "محمد"
|
||
givenName_romanized: "Mehmed"
|
||
title: "افندی (Efendi)"
|
||
patronymic: "بن احمد"
|
||
patronymic_romanized: "bin Ahmed"
|
||
roles:
|
||
- role_title: "مشتری (müşteri)"
|
||
role_in_source: "buyer"
|
||
biographical:
|
||
sex: "male"
|
||
residence: "Demirciköy"
|
||
social_rank: "Efendi (educated class)"
|
||
family_relationships:
|
||
father:
|
||
- name: "احمد (Ahmed)"
|
||
spouse:
|
||
- person_index: 2
|
||
target_name: "Fatma Hatun"
|
||
context: "Buyer, Efendi = literate/administrative"
|
||
|
||
- person_index: 2
|
||
pnv_name:
|
||
literalName: "فاطمه خاتون بنت علیاوغلو"
|
||
literalName_romanized: "Fatma Hatun bint Ali-oğlu"
|
||
givenName: "فاطمه"
|
||
givenName_romanized: "Fatma"
|
||
title: "خاتون (Hatun)"
|
||
patronymic: "بنت علیاوغلو"
|
||
patronymic_romanized: "bint Ali-oğlu"
|
||
roles:
|
||
- role_title: "مشتری (müşteri)"
|
||
role_in_source: "buyer"
|
||
- role_title: "زوجه (zevce)"
|
||
role_in_source: "wife"
|
||
biographical:
|
||
sex: "female"
|
||
marital_status: "married"
|
||
social_rank: "Hatun (respectable woman)"
|
||
family_relationships:
|
||
father:
|
||
- name: "علیاوغلو (Ali-oğlu)"
|
||
spouse:
|
||
- person_index: 1
|
||
target_name: "Mehmed Efendi"
|
||
context: "Wife of buyer, co-purchaser"
|
||
|
||
- person_index: 3
|
||
pnv_name:
|
||
literalName: "حسن افندی بن عمر"
|
||
literalName_romanized: "Hasan Efendi bin Ömer"
|
||
givenName: "حسن"
|
||
givenName_romanized: "Hasan"
|
||
title: "افندی (Efendi)"
|
||
patronymic: "بن عمر"
|
||
patronymic_romanized: "bin Ömer"
|
||
roles:
|
||
- role_title: "شاهد (şahid)"
|
||
role_in_source: "witness"
|
||
biographical:
|
||
sex: "male"
|
||
social_rank: "Efendi"
|
||
family_relationships:
|
||
father:
|
||
- name: "عمر (Ömer)"
|
||
context: "First witness"
|
||
|
||
- person_index: 4
|
||
pnv_name:
|
||
literalName: "ابراهیم چلبی بن مصطفی"
|
||
literalName_romanized: "İbrahim Çelebi bin Mustafa"
|
||
givenName: "ابراهیم"
|
||
givenName_romanized: "İbrahim"
|
||
title: "چلبی (Çelebi)"
|
||
patronymic: "بن مصطفی"
|
||
patronymic_romanized: "bin Mustafa"
|
||
roles:
|
||
- role_title: "شاهد (şahid)"
|
||
role_in_source: "witness"
|
||
biographical:
|
||
sex: "male"
|
||
social_rank: "Çelebi (gentleman/merchant)"
|
||
family_relationships:
|
||
father:
|
||
- name: "مصطفی (Mustafa)"
|
||
context: "Second witness"
|
||
|
||
temporal_references:
|
||
- expression: "فی اوائل شهر رجب سنة ١٢٥٨"
|
||
expression_romanized: "fi evail-i şehr-i Receb sene 1258"
|
||
normalized: "1842-07"
|
||
calendar: "Hijri"
|
||
type: "DATE"
|
||
conversion_note: "Receb 1258 AH ≈ July-August 1842 CE"
|
||
|
||
locations_mentioned:
|
||
- name: "قصبه دميرجیکوی"
|
||
name_romanized: "kasaba Demirciköy"
|
||
type: "town (kasaba)"
|
||
- name: "مجلس شرع شريف"
|
||
name_romanized: "meclis-i şer'-i şerif"
|
||
type: "court"
|
||
|
||
ottoman_naming_notes: |
|
||
Ottoman Turkish naming conventions:
|
||
|
||
HONORIFIC TITLES:
|
||
- آغا (Ağa): Military commander, landowner
|
||
- افندی (Efendi): Educated person, official
|
||
- چلبی (Çelebi): Gentleman, merchant
|
||
- خاتون (Hatun): Respectable woman
|
||
|
||
PATRONYMIC PATTERNS:
|
||
- بن (bin): Son of (Arabic)
|
||
- بنت (bint): Daughter of (Arabic)
|
||
- اوغلو (-oğlu): Son of (Turkish)
|
||
|
||
DECEASED MARKERS:
|
||
- مرحوم (merhum): The late (man)
|
||
- مرحومه (merhume): The late (woman)
|
||
|
||
CALENDAR: Hijri lunar (354/355 days)
|
||
Receb 1258 AH ≈ July-August 1842 CE
|
||
|
||
provenance:
|
||
data_status: "SYNTHETIC_EXAMPLE"
|
||
notes: |
|
||
This example uses synthetic data based on authentic Ottoman Turkish
|
||
sijill (court register) formulae for demonstration purposes. Names,
|
||
dates, and locations are fictional but follow authentic 19th-century
|
||
patterns. For real examples, see PROVENANCE_SOURCES.md.
|
||
|
||
related_real_sources:
|
||
- archive: "OpenJerusalem Project"
|
||
collection: "Jerusalem Sharia Court Registers"
|
||
digital_url: "https://www.openjerusalem.org/"
|
||
ark_identifier: "ark:/58142/PfV7b"
|
||
volume_count: "102 registers"
|
||
period: "1834-1920 CE"
|
||
languages: "Ottoman Turkish, Arabic"
|
||
license: "Open Access"
|
||
document_types: "Property sales, marriage contracts, inheritance, waqf"
|
||
|
||
- archive: "İslam Araştırmaları Merkezi (ISAM)"
|
||
collection: "Istanbul Kadı Sicilleri"
|
||
digital_url: "http://www.kadisicilleri.org/"
|
||
volume_count: "40+ volumes online"
|
||
document_count: "40,000+ documents"
|
||
period: "16th-19th century CE"
|
||
language: "Ottoman Turkish"
|
||
license: "Research access"
|
||
|
||
- archive: "Istanbul Metropolitan Municipality"
|
||
project: "History of Istanbul"
|
||
digital_url: "https://istanbultarihi.ist/434-istanbul-sharia-court-registers"
|
||
volume_count: "~10,000 volumes"
|
||
courts: "26 different courts"
|
||
period: "1453-1922 CE"
|
||
notes: "Largest collection of Ottoman court records in existence"
|
||
|
||
- archive: "Harvard University"
|
||
project: "Ottoman Court Records Project (OCRP)"
|
||
digital_url: "https://cmes.fas.harvard.edu/projects/ocrp"
|
||
document_types: "Sijill transcriptions, translations"
|
||
period: "16th-19th century CE"
|
||
|
||
# =============================================================================
|
||
# END OF MODULE
|
||
# =============================================================================
|