glam/data/entity_annotation/modules/relationships/family.yaml
kempersc 505c12601a Add test script for PiCo extraction from Arabic waqf documents
- Implemented a new script `test_pico_arabic_waqf.py` to test the GLM annotator's ability to extract person observations from Arabic historical documents.
- The script includes environment variable handling for API token, structured prompts for the GLM API, and validation of extraction results.
- Added comprehensive logging for API responses, extraction results, and validation errors.
- Included a sample Arabic waqf text for testing purposes, following the PiCo ontology pattern.
2025-12-12 17:50:17 +01:00

1503 lines
56 KiB
YAML
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# =============================================================================
# CH-Annotator Entity Annotation Convention v1.7.0
# Module: relationships/family.yaml
# =============================================================================
# Family relationship properties from PiCo (Person in Context) ontology.
# These enable modeling complex family structures from historical records.
#
# This module is referenced by integrations/pico.yaml
#
# References:
# - PiCo Ontology: https://w3id.org/pico
# - Schema.org: https://schema.org/
# =============================================================================
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:
description: "Basic family relationships using Schema.org vocabulary"
properties:
- 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:
description: "Transitive properties for ancestor/descendant chains"
properties:
- 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:
description: "Multi-generational direct line relationships"
properties:
- property: "pico:hasGrandparent"
property_uri: "https://personsincontext.org/model#hasGrandparent"
description: "A grandparent of the person"
inverse: "pico:hasGrandchild"
- property: "pico:hasGrandchild"
property_uri: "https://personsincontext.org/model#hasGrandchild"
description: "A grandchild of the person"
inverse: "pico:hasGrandparent"
- property: "pico:hasGreat-grandparent"
property_uri: "https://personsincontext.org/model#hasGreat-grandparent"
description: "A great-grandparent of the person"
inverse: "pico:hasGreat-grandchild"
- property: "pico:hasGreat-grandchild"
property_uri: "https://personsincontext.org/model#hasGreat-grandchild"
description: "A great-grandchild of the person"
inverse: "pico:hasGreat-grandparent"
# ---------------------------------------------------------------------------
# Aunts/Uncles and Nieces/Nephews
# ---------------------------------------------------------------------------
extended_family:
description: "Collateral relatives (aunts, uncles, cousins)"
properties:
- 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:
description: "Step-family relationships through remarriage"
properties:
- 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"
description: "A stepchild (child of spouse)"
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)
# ---------------------------------------------------------------------------
non_biological_relationships:
description: "Non-biological family relationships (foster, godparent, legitimized)"
properties:
- property: "pico:hasFosterParent"
property_uri: "https://personsincontext.org/model#hasFosterParent"
description: "A foster parent"
inverse: "pico:hasFosterChild"
- property: "pico:hasFosterChild"
property_uri: "https://personsincontext.org/model#hasFosterChild"
description: "A foster child"
inverse: "pico:hasFosterParent"
- property: "pico:hasGodparent"
property_uri: "https://personsincontext.org/model#hasGodparent"
description: "A godparent (witness at baptism)"
inverse: "pico:hasGodchild"
note: "Critical for historical genealogical research - baptism records"
- property: "pico:hasGodchild"
property_uri: "https://personsincontext.org/model#hasGodchild"
description: "A godchild"
inverse: "pico:hasGodparent"
- property: "pico:hasLegitimizedChild"
property_uri: "https://personsincontext.org/model#hasLegitimizedChild"
description: "A child legitimized by marriage or legal recognition"
inverse: "pico:isLegitimizedChildOf"
note: "Common in historical records when child born out of wedlock"
- property: "pico:isLegitimizedChildOf"
property_uri: "https://personsincontext.org/model#isLegitimizedChildOf"
description: "The parent who legitimized the child"
inverse: "pico:hasLegitimizedChild"
# ---------------------------------------------------------------------------
# In-Laws
# ---------------------------------------------------------------------------
in_law_relationships:
description: "Relationships through marriage (in-laws)"
properties:
- property: "pico:hasParent-in-law"
property_uri: "https://personsincontext.org/model#hasParent-in-law"
description: "A parent-in-law (parent of spouse)"
inverse: "pico:hasChild-in-law"
- property: "pico:hasChild-in-law"
property_uri: "https://personsincontext.org/model#hasChild-in-law"
description: "A child-in-law (spouse of child)"
inverse: "pico:hasParent-in-law"
- property: "pico:hasSibling-in-law"
property_uri: "https://personsincontext.org/model#hasSibling-in-law"
description: "A brother/sister-in-law"
symmetric: true
- property: "pico:hasGrandparent-in-law"
property_uri: "https://personsincontext.org/model#hasGrandparent-in-law"
description: "A grandparent-in-law"
inverse: "pico:hasGrandchild-in-law"
- property: "pico:hasGrandchild-in-law"
property_uri: "https://personsincontext.org/model#hasGrandchild-in-law"
description: "A grandchild-in-law"
inverse: "pico:hasGrandparent-in-law"
- property: "pico:hasUncle_Aunt-in-law"
property_uri: "https://personsincontext.org/model#hasUncle_Aunt-in-law"
description: "An uncle/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"
description: "A nephew/niece-in-law"
inverse: "pico:hasUncle_Aunt-in-law"
- property: "pico:hasCousin-in-law"
property_uri: "https://personsincontext.org/model#hasCousin-in-law"
description: "A cousin-in-law"
symmetric: true
- property: "pico:hasStepparent-in-law"
property_uri: "https://personsincontext.org/model#hasStepparent-in-law"
description: "A stepparent-in-law"
inverse: "pico:hasStepchild-in-law"
- property: "pico:hasStepchild-in-law"
property_uri: "https://personsincontext.org/model#hasStepchild-in-law"
description: "A stepchild-in-law"
inverse: "pico:hasStepparent-in-law"
# ---------------------------------------------------------------------------
# Former Partners
# ---------------------------------------------------------------------------
former_partner_relationships:
description: "Relationships with deceased or former spouses"
properties:
- property: "pico:isWidOf"
property_uri: "https://personsincontext.org/model#isWidOf"
description: "Is widow/widower of deceased spouse"
note: "The subject is the surviving partner; critical for historical records"
- property: "pico:hasPreviousPartner"
property_uri: "https://personsincontext.org/model#hasPreviousPartner"
description: "A former spouse or partner"
symmetric: true
# =============================================================================
# Relationship Type Summary
# =============================================================================
relationship_summary:
total_properties: 34
by_category:
core_family: 4
ancestry: 2
grandparent: 4
extended_family: 3
step_family: 4
non_biological: 6
in_law: 9
former_partners: 2
symmetric_properties:
- "sdo:spouse"
- "sdo:sibling"
- "pico:hasCousin"
- "pico:hasStepsibling"
- "pico:hasHalf-sibling"
- "pico:hasSibling-in-law"
- "pico:hasCousin-in-law"
- "pico:hasPreviousPartner"
transitive_properties:
- "pico:hasAncestor"
- "pico:hasDescendant"
# =============================================================================
# GLM Extraction Output Schema (for family_relationships field)
# =============================================================================
extraction_output_schema:
description: |
Schema for the family_relationships object in GLM extraction output.
All arrays contain person references with person_index and target_name.
schema:
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"
person_reference_format:
person_index: "integer (0-based index into persons array)"
target_name: "string (name for readability)"
example:
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"
# =============================================================================
# Historical Source Patterns
# =============================================================================
historical_source_patterns:
description: |
Common patterns for expressing family relationships in historical sources,
organized by language. Used for extraction guidance.
dutch:
spouse:
- "huijsvrou van" # wife of
- "echtgenoot van" # husband of
- "gehuwd met" # married to
- "vrouw van" # wife of
- "man van" # husband of
parent:
- "zoon van" # son of
- "dochter van" # daughter of
- "kind van" # child of
- "vader van" # father of
- "moeder van" # mother of
widow:
- "weduwe van" # widow of (female)
- "weduwnaar van" # widower of (male)
- "wijlen" # the late (indicates deceased)
godparent:
- "peter" # godfather
- "meter" # godmother
- "getuijge" # witness (often godparent at baptism)
- "doopgetuige" # baptismal witness
sibling:
- "broeder van" # brother of
- "zuster van" # sister of
latin:
parent:
- "filius" # son
- "filia" # daughter
- "pater" # father
- "mater" # mother
spouse:
- "uxor" # wife
- "maritus" # husband
- "conjux" # spouse
widow:
- "vidua" # widow
- "viduus" # widower
- "quondam" # the late
german:
spouse:
- "Ehefrau von" # wife of
- "Ehemann von" # husband of
- "verheiratet mit" # married to
parent:
- "Sohn von" # son of
- "Tochter von" # daughter of
- "Vater von" # father of
- "Mutter von" # mother of
widow:
- "Witwe von" # widow of
- "Witwer von" # widower of
# ---------------------------------------------------------------------------
# Arabic (العربية) - Common in Ottoman records, Islamic archives, waqf documents
# Note: Includes both Modern Standard Arabic and common dialectal variants
# ---------------------------------------------------------------------------
arabic:
description: |
Arabic naming conventions use patronymic chains (nasab) with ibn/bint,
honorific titles (laqab), occupational names (nisba), and tribal/regional
affiliations. Common in Ottoman court records, waqf documents, Islamic
marriage contracts (aqd nikah), and genealogical registers (shajara).
# Patronymic/parentage (nasab - نسب)
parent:
- "ابن" # ibn - son of (formal)
- "بن" # bin - son of (abbreviated, common in names)
- "بنت" # bint - daughter of
- "أب" # ab - father
- "أبو" # abu - father of (kunya)
- "أم" # umm - mother / mother of (kunya)
- "والد" # walid - father
- "والدة" # walida - mother
- "ولد" # walad - child/son
- "أبوه" # abuhu - his father
- "أمه" # ummuhu - his mother
# Spouse relationships
spouse:
- "زوج" # zawj - husband
- "زوجة" # zawja - wife
- "زوجته" # zawjatuhu - his wife
- "زوجها" # zawjuha - her husband
- "امرأة" # imra'a - woman/wife of
- "حرم" # haram - wife (honorific, lit. "sanctuary")
- "عقيلة" # aqila - wife (formal)
- "قرينة" # qarina - spouse/companion
- "متزوج من" # mutazawwij min - married to (male)
- "متزوجة من" # mutazawwija min - married to (female)
# Widow/widower
widow:
- "أرملة" # armala - widow
- "أرمل" # armal - widower
- "المرحوم" # al-marhum - the late (male, deceased)
- "المرحومة" # al-marhuma - the late (female, deceased)
- "المتوفى" # al-mutawaffa - the deceased (male)
- "المتوفاة" # al-mutawaffat - the deceased (female)
- "رحمه الله" # rahimahu Allah - may God have mercy on him
- "رحمها الله" # rahimaha Allah - may God have mercy on her
# Siblings
sibling:
- "أخ" # akh - brother
- "أخت" # ukht - sister
- "شقيق" # shaqiq - full brother (same parents)
- "شقيقة" # shaqiqa - full sister (same parents)
- "أخوه" # akhuhu - his brother
- "أختها" # ukhtuha - her sister
# Grandparents/grandchildren
grandparent:
- "جد" # jadd - grandfather
- "جدة" # jadda - grandmother
- "حفيد" # hafid - grandson
- "حفيدة" # hafida - granddaughter
# Extended family
extended:
- "عم" # 'amm - paternal uncle
- "عمة" # 'amma - paternal aunt
- "خال" # khal - maternal uncle
- "خالة" # khala - maternal aunt
- "ابن عم" # ibn 'amm - paternal cousin (male)
- "بنت عم" # bint 'amm - paternal cousin (female)
- "ابن خال" # ibn khal - maternal cousin (male)
- "بنت خال" # bint khal - maternal cousin (female)
# In-laws (أصهار - ashar)
in_law:
- "حمو" # hamu - father-in-law
- "حماة" # hamah - mother-in-law
- "صهر" # sihr - son-in-law / brother-in-law
- "كنة" # kanna - daughter-in-law
- "نسيب" # nasib - in-law relation
- "سلف" # silf - co-brother-in-law
- "سلفة" # silfa - co-sister-in-law
# Step-relations
step_family:
- "ربيب" # rabib - stepson
- "ربيبة" # rabiba - stepdaughter
- "زوج الأم" # zawj al-umm - stepfather
- "زوجة الأب" # zawjat al-ab - stepmother
# Orphan/guardian (common in waqf documents)
guardian:
- "يتيم" # yatim - orphan (fatherless)
- "وصي" # wasi - guardian/executor
- "كفيل" # kafil - sponsor/guarantor
- "حاضن" # hadin - custodian
# Tribal/clan affiliations (common in genealogies)
tribal:
- "آل" # Al - family of / house of
- "بني" # Bani - sons of (tribe)
- "قبيلة" # qabila - tribe
- "عشيرة" # 'ashira - clan
# ---------------------------------------------------------------------------
# French (for North African/Ottoman archives)
# ---------------------------------------------------------------------------
french:
spouse:
- "épouse de" # wife of
- "époux de" # husband of
- "marié à" # married to (male)
- "mariée à" # married to (female)
parent:
- "fils de" # son of
- "fille de" # daughter of
- "père de" # father of
- "mère de" # mother of
widow:
- "veuve de" # widow of
- "veuf de" # widower of
- "feu" # the late (male)
- "feue" # the late (female)
sibling:
- "frère de" # brother of
- "sœur de" # sister of
# ---------------------------------------------------------------------------
# Ottoman Turkish (for Ottoman archival records)
# ---------------------------------------------------------------------------
ottoman_turkish:
description: |
Ottoman Turkish used Arabic script and incorporated Arabic/Persian
terminology. Common in court registers (sicil), tax records (tahrir),
and endowment documents (vakfiye).
parent:
- "oğlu" # son of (Turkish suffix)
- "kızı" # daughter of (Turkish suffix)
- "ibn" # son of (Arabic, used in Ottoman)
- "bint" # daughter of (Arabic, used in Ottoman)
- "veled-i" # child of (Persian-Turkish)
- "mahdumu" # son of (Persian honorific)
spouse:
- "zevcesi" # his wife
- "zevci" # her husband
- "haremi" # his wife (from harem)
- "nikâhlı" # legally married
widow:
- "dul" # widow/widower
- "müteveffa" # the deceased (male)
- "müteveffiye" # the deceased (female)
- "merhum" # the late (male)
- "merhume" # the late (female)
# ---------------------------------------------------------------------------
# Hebrew (עברית) - Jewish archives, genizah documents, rabbinic records
# Note: Includes both Biblical/Rabbinic Hebrew and modern Israeli Hebrew
# ---------------------------------------------------------------------------
hebrew:
description: |
Hebrew naming conventions in Jewish records include patronymics (ben/bat),
tribal affiliations (ha-Kohen, ha-Levi), honorifics, and memorial phrases.
Common in ketubbot (marriage contracts), get documents (divorce), pinqasim
(community records), genizah fragments, and rabbinic responsa.
# Patronymic/parentage
parent:
- "בן" # ben - son of
- "בת" # bat - daughter of
- "אבי" # avi - my father
- "אמי" # imi - my mother
- "אב" # av - father
- "אם" # em - mother
- "בנו של" # beno shel - his son
- "בתו של" # bito shel - his daughter
- "ילד" # yeled - child (male)
- "ילדה" # yalda - child (female)
# Spouse relationships
spouse:
- "אשת" # eshet - wife of
- "בעל" # ba'al - husband
- "אישה" # isha - wife/woman
- "זוג" # zug - spouse (modern)
- "זוגתו" # zugato - his spouse (female)
- "נשוי ל" # nasui le - married to (male)
- "נשואה ל" # nesu'a le - married to (female)
- "כלה" # kala - bride
- "חתן" # chatan - groom
# Widow/widower
widow:
- "אלמנה" # almana - widow
- "אלמן" # alman - widower
- "ז״ל" # z"l (zikhronó livrakha) - of blessed memory
- "ע״ה" # a"h (alav/aleha hashalom) - peace be upon him/her
- "הי״ד" # hy"d (Hashem yinkom damo) - may God avenge his blood (martyrs)
- "נ״ע" # n"e (nishmatá eden) - may their soul be in Eden
- "המנוח" # ha-manoakh - the late (male)
- "המנוחה" # ha-menukha - the late (female)
# Siblings
sibling:
- "אח" # akh - brother
- "אחות" # akhot - sister
- "אחיו" # akhiv - his brother
- "אחותו" # akhoto - his sister
# Grandparents/grandchildren
grandparent:
- "סב" # sav - grandfather
- "סבתא" # savta - grandmother
- "נכד" # nekhed - grandson
- "נכדה" # nekhda - granddaughter
# Extended family
extended:
- "דוד" # dod - uncle
- "דודה" # doda - aunt
- "בן דוד" # ben dod - cousin (male)
- "בת דודה" # bat doda - cousin (female)
# In-laws
in_law:
- "חם" # kham - father-in-law
- "חמות" # khamot - mother-in-law
- "חתן" # khatan - son-in-law
- "כלה" # kala - daughter-in-law
- "גיס" # gis - brother-in-law
- "גיסה" # gisa - sister-in-law
# Tribal/priestly affiliations (common in Jewish records)
tribal:
- "הכהן" # ha-Kohen - the Priest (Kohen lineage)
- "הלוי" # ha-Levi - the Levite
- "כ״ץ" # KaTz - abbreviation for Kohen Tzedek
- "סג״ל" # SeGaL - abbreviation for Segan Leviya
# Honorifics (common in rabbinic records)
honorifics:
- "רב" # rav - rabbi
- "ר׳" # r' - rabbi (abbreviated)
- "הרב" # ha-rav - the rabbi
- "מורנו" # morenu - our teacher
- "מר" # mar - mister (Aramaic/Hebrew)
- "מרת" # marat - mistress/Mrs.
- "החכם" # ha-khakham - the sage (Sephardic)
- "הגאון" # ha-gaon - the genius (high honorific)
# ---------------------------------------------------------------------------
# Persian/Farsi (فارسی) - Iranian archives, Safavid/Qajar documents
# ---------------------------------------------------------------------------
persian:
description: |
Persian naming conventions blend Arabic Islamic patterns with indigenous
Iranian elements. Common in Safavid court records, Qajar-era documents,
endowment deeds (vaqfnameh), and judicial records (mahzar).
# Patronymic/parentage
parent:
- "پسر" # pesar - son
- "دختر" # dokhtar - daughter
- "فرزند" # farzand - child/offspring
- "پدر" # pedar - father
- "مادر" # madar - mother
- "ابن" # ebn - son of (Arabic loanword, formal)
- "بنت" # bent - daughter of (Arabic loanword, formal)
- "ولد" # valad - child of
# Spouse relationships
spouse:
- "شوهر" # showhar - husband
- "زن" # zan - wife/woman
- "همسر" # hamsar - spouse
- "عیال" # ayal - wife (formal/classical)
- "زوجه" # zowjeh - wife (Arabic loanword)
- "زوج" # zowj - husband (Arabic loanword)
- "عقد" # aqd - marriage contract
- "نکاح" # nekah - marriage
# Widow/widower
widow:
- "بیوه" # biveh - widow
- "بیوه‌مرد" # biveh-mard - widower
- "مرحوم" # marhum - the late (male)
- "مرحومه" # marhumeh - the late (female)
- "متوفی" # motevaffa - the deceased (male)
- "متوفیه" # motevaffiyeh - the deceased (female)
- "شادروان" # shadravan - the late (respectful)
- "درگذشته" # dargozashteh - passed away
# Siblings
sibling:
- "برادر" # baradar - brother
- "خواهر" # khahar - sister
# Grandparents/grandchildren
grandparent:
- "پدربزرگ" # pedarbozorg - grandfather
- "مادربزرگ" # madarbozorg - grandmother
- "نوه" # naveh - grandchild
# Extended family
extended:
- "عمو" # amu - paternal uncle
- "عمه" # ammeh - paternal aunt
- "دایی" # dayi - maternal uncle
- "خاله" # khaleh - maternal aunt
- "پسرعمو" # pesar-amu - paternal cousin (male)
- "دخترعمو" # dokhtar-amu - paternal cousin (female)
# In-laws
in_law:
- "پدرشوهر" # pedar-showhar - father-in-law (husband's father)
- "مادرشوهر" # madar-showhar - mother-in-law (husband's mother)
- "پدرزن" # pedar-zan - father-in-law (wife's father)
- "مادرزن" # madar-zan - mother-in-law (wife's mother)
- "داماد" # damad - son-in-law
- "عروس" # arus - daughter-in-law/bride
- "باجناق" # bajnaq - co-brother-in-law
# Titles and honorifics
honorifics:
- "آقا" # aqa - mister/sir
- "خانم" # khanom - lady/Mrs.
- "میرزا" # mirza - educated man/scribe
- "خان" # khan - lord/chief
- "بیگم" # begom - lady (Turkic origin)
- "سلطان" # soltan - sultan/ruler
- "شاهزاده" # shahzadeh - prince/princess
# ---------------------------------------------------------------------------
# Spanish (Español) - Colonial Latin America, Iberian archives
# ---------------------------------------------------------------------------
spanish:
description: |
Spanish colonial records include civil and ecclesiastical documents from
Latin America, Philippines, and Spain. Common in padrones (censuses),
testamentos (wills), actas de bautismo/matrimonio/defunción (vital records),
and Inquisition proceedings.
# Parentage
parent:
- "hijo de" # son of
- "hija de" # daughter of
- "hijo legítimo de" # legitimate son of
- "hija legítima de" # legitimate daughter of
- "hijo natural de" # illegitimate son of
- "hija natural de" # illegitimate daughter of
- "padre" # father
- "madre" # mother
- "padres" # parents
- "progenitor" # progenitor
# Spouse relationships
spouse:
- "esposo de" # husband of
- "esposa de" # wife of
- "marido de" # husband of
- "mujer de" # wife of (also "woman of")
- "casado con" # married to (male)
- "casada con" # married to (female)
- "consorte" # consort/spouse
- "cónyuge" # spouse (legal)
- "desposado con" # betrothed to
- "velado con" # veiled with (church wedding)
# Widow/widower
widow:
- "viuda de" # widow of
- "viudo de" # widower of
- "difunto" # the deceased (male)
- "difunta" # the deceased (female)
- "finado" # the late (male)
- "finada" # the late (female)
- "que en paz descanse" # may they rest in peace
- "q.e.p.d." # que en paz descanse (abbreviated)
- "que santa gloria haya" # may they have holy glory
# Siblings
sibling:
- "hermano de" # brother of
- "hermana de" # sister of
- "medio hermano" # half-brother
- "media hermana" # half-sister
- "hermanastro" # stepbrother
- "hermanastra" # stepsister
# Grandparents/grandchildren
grandparent:
- "abuelo" # grandfather
- "abuela" # grandmother
- "nieto de" # grandson of
- "nieta de" # granddaughter of
- "bisabuelo" # great-grandfather
- "bisabuela" # great-grandmother
# Extended family
extended:
- "tío" # uncle
- "tía" # aunt
- "sobrino" # nephew
- "sobrina" # niece
- "primo" # cousin (male)
- "prima" # cousin (female)
- "primo hermano" # first cousin (male)
- "prima hermana" # first cousin (female)
# In-laws
in_law:
- "suegro" # father-in-law
- "suegra" # mother-in-law
- "yerno" # son-in-law
- "nuera" # daughter-in-law
- "cuñado" # brother-in-law
- "cuñada" # sister-in-law
- "consuegro" # co-father-in-law
- "consuegra" # co-mother-in-law
# Step-relations
step_family:
- "padrastro" # stepfather
- "madrastra" # stepmother
- "hijastro" # stepson
- "hijastra" # stepdaughter
- "entenado" # stepchild (archaic)
- "entenada" # stepdaughter (archaic)
# Godparent relationships (very important in colonial records)
godparent:
- "padrino" # godfather
- "madrina" # godmother
- "ahijado" # godson
- "ahijada" # goddaughter
- "compadre" # co-father (godparent relationship)
- "comadre" # co-mother (godparent relationship)
# Legal/social status (colonial casta system)
status:
- "don" # honorific for male
- "doña" # honorific for female
- "indio/india" # indigenous person
- "mestizo/mestiza" # mixed Spanish-indigenous
- "mulato/mulata" # mixed African heritage
- "español/española" # Spanish descent
- "criollo/criolla" # American-born Spanish
- "libre" # free (for formerly enslaved)
- "esclavo/esclava" # enslaved person
# ---------------------------------------------------------------------------
# Portuguese (Português) - Colonial Brazil, African archives, Lusophone world
# ---------------------------------------------------------------------------
portuguese:
description: |
Portuguese colonial records span Brazil, Angola, Mozambique, Goa, Macau,
and other territories. Common in registros paroquiais (parish registers),
inventários (estate inventories), testamentos (wills), and Inquisition
proceedings.
# Parentage
parent:
- "filho de" # son of
- "filha de" # daughter of
- "filho legítimo de" # legitimate son of
- "filha legítima de" # legitimate daughter of
- "filho natural de" # illegitimate son of
- "filha natural de" # illegitimate daughter of
- "pai" # father
- "mãe" # mother
- "pais" # parents
- "progenitor" # progenitor
# Spouse relationships
spouse:
- "esposo de" # husband of
- "esposa de" # wife of
- "marido de" # husband of
- "mulher de" # wife of
- "casado com" # married to (male)
- "casada com" # married to (female)
- "cônjuge" # spouse (legal)
- "consorte" # consort
- "desposado com" # betrothed to
# Widow/widower
widow:
- "viúva de" # widow of
- "viúvo de" # widower of
- "defunto" # the deceased (male)
- "defunta" # the deceased (female)
- "falecido" # the late (male)
- "falecida" # the late (female)
- "finado" # the late (male)
- "finada" # the late (female)
- "que Deus haja" # whom God has (taken)
# Siblings
sibling:
- "irmão de" # brother of
- "irmã de" # sister of
- "meio-irmão" # half-brother
- "meia-irmã" # half-sister
# Grandparents/grandchildren
grandparent:
- "avô" # grandfather
- "avó" # grandmother
- "neto de" # grandson of
- "neta de" # granddaughter of
- "bisavô" # great-grandfather
- "bisavó" # great-grandmother
# Extended family
extended:
- "tio" # uncle
- "tia" # aunt
- "sobrinho" # nephew
- "sobrinha" # niece
- "primo" # cousin (male)
- "prima" # cousin (female)
- "primo direito" # first cousin (male)
- "prima direita" # first cousin (female)
# In-laws
in_law:
- "sogro" # father-in-law
- "sogra" # mother-in-law
- "genro" # son-in-law
- "nora" # daughter-in-law
- "cunhado" # brother-in-law
- "cunhada" # sister-in-law
- "consogro" # co-father-in-law
- "consogra" # co-mother-in-law
# Step-relations
step_family:
- "padrasto" # stepfather
- "madrasta" # stepmother
- "enteado" # stepson
- "enteada" # stepdaughter
# Godparent relationships
godparent:
- "padrinho" # godfather
- "madrinha" # godmother
- "afilhado" # godson
- "afilhada" # goddaughter
- "compadre" # co-father (godparent relationship)
- "comadre" # co-mother (godparent relationship)
# Legal/social status (colonial Brazil)
status:
- "dom" # honorific for male
- "dona" # honorific for female
- "índio/índia" # indigenous person
- "mameluco/mameluca" # mixed Portuguese-indigenous
- "mulato/mulata" # mixed African heritage
- "pardo/parda" # mixed-race (general)
- "preto/preta" # Black person
- "branco/branca" # White person
- "forro/forra" # freed person
- "escravo/escrava" # enslaved person
- "liberto/liberta" # freedperson
- "crioulo/crioula" # Brazilian-born Black person
# =============================================================================
# ITALIAN HISTORICAL PATTERNS
# =============================================================================
# Coverage: Italian states (Papal States, Venice, Naples, etc.), 15th-19th century
# Script: Latin
# =============================================================================
italian:
description: |
Italian historical documents include notarial acts, parish registers,
catasti (censuses), and stato delle anime (status animarum - soul records).
Naming follows patronymic patterns with "di" or "fu" (the late),
with regional variations across Italian states.
source_types:
- "atti notarili" # notarial acts
- "registri parrocchiali" # parish registers
- "stato delle anime" # status animarum (census of souls)
- "catasto" # tax census
- "liber baptizatorum" # baptismal register
- "liber matrimoniorum" # marriage register
- "liber mortuorum" # death register
patterns:
# Child-parent relationships
child_of:
- "figlio di" # son of
- "figlia di" # daughter of
- "figlio del fu" # son of the late
- "figlia del fu" # daughter of the late
- "figlio della fu" # son of the late (female)
- "figlia della fu" # daughter of the late (female)
- "figlio legittimo di" # legitimate son of
- "figlia legittima di" # legitimate daughter of
- "figlio naturale di" # natural (illegitimate) son of
- "figlia naturale di" # natural (illegitimate) daughter of
- "nato da" # born of
- "nata da" # born of (female)
- "di padre" # of father
- "di madre" # of mother
- "q." # abbreviation for quondam (the late)
- "fu" # the late (abbreviated from "fu il")
- "del fu" # of the late (male)
- "della fu" # of the late (female)
# Spouse relationships
spouse:
- "marito di" # husband of
- "moglie di" # wife of
- "sposo di" # spouse of (male)
- "sposa di" # spouse of (female)
- "consorte di" # consort of
- "coniuge di" # spouse of (legal)
- "maritata con" # married to (female subject)
- "maritato con" # married to (male subject)
- "sposata con" # married to (female)
- "sposato con" # married to (male)
- "uxor" # wife (Latin in Italian documents)
# Widow/widower
widow:
- "vedova di" # widow of
- "vedovo di" # widower of
- "relicta di" # widow of (Latin: left behind by)
- "relicta del fu" # widow of the late
- "vidua" # widow (Latin)
# Siblings
sibling:
- "fratello di" # brother of
- "sorella di" # sister of
- "germano" # full sibling
- "germana" # full sibling (female)
- "fratello uterino" # maternal half-brother
- "sorella uterina" # maternal half-sister
- "fratello consanguineo" # paternal half-brother
- "sorella consanguinea" # paternal half-sister
# Grandparents/grandchildren
grandparent:
- "nonno" # grandfather
- "nonna" # grandmother
- "avo" # grandfather (archaic)
- "ava" # grandmother (archaic)
- "nipote di" # grandchild/nephew/niece of
- "bisnonno" # great-grandfather
- "bisnonna" # great-grandmother
- "trisavolo" # great-great-grandfather
- "trisavola" # great-great-grandmother
# Extended family
extended:
- "zio" # uncle
- "zia" # aunt
- "nipote" # nephew/niece/grandchild
- "cugino" # cousin (male)
- "cugina" # cousin (female)
- "cugino germano" # first cousin (male)
- "cugina germana" # first cousin (female)
# In-laws
in_law:
- "suocero" # father-in-law
- "suocera" # mother-in-law
- "genero" # son-in-law
- "nuora" # daughter-in-law
- "cognato" # brother-in-law
- "cognata" # sister-in-law
# Step-relations
step_family:
- "patrigno" # stepfather
- "matrigna" # stepmother
- "figliastro" # stepson
- "figliastra" # stepdaughter
# Godparent relationships
godparent:
- "padrino" # godfather
- "madrina" # godmother
- "figlioccio" # godson
- "figlioccia" # goddaughter
- "compare" # co-father (spiritual kinship)
- "comare" # co-mother (spiritual kinship)
- "patrino" # godfather (archaic)
- "matrina" # godmother (archaic)
# Honorifics and titles
honorifics:
- "Messer" # Mister (medieval/Renaissance)
- "Madonna" # My lady (medieval/Renaissance)
- "Ser" # Sir (notarial)
- "Don" # Lord (clergy, nobility)
- "Donna" # Lady
- "Signor" # Mister
- "Signora" # Mrs.
- "Illustrissimo" # Most illustrious
- "Eccellentissimo" # Most excellent
- "Magnifico" # Magnificent (Venetian nobility)
- "Nobil Homo" # Noble man (Venetian)
- "Nobil Donna" # Noble woman (Venetian)
# Deceased markers
deceased:
- "fu" # the late
- "quondam" # the late (Latin)
- "q." # abbreviation for quondam
- "bone memorie" # of good memory
- "defunto" # deceased (male)
- "defunta" # deceased (female)
- "morto" # dead (male)
- "morta" # dead (female)
# Occupation/status indicators
status:
- "cittadino" # citizen
- "abitante" # resident
- "forestiero" # foreigner
- "nobile" # noble
- "popolano" # commoner
- "contadino" # peasant
- "artigiano" # artisan
- "mercante" # merchant
# =============================================================================
# GREEK HISTORICAL PATTERNS
# =============================================================================
# Coverage: Byzantine, Ottoman-era Greek, Modern Greek
# Script: Greek
# =============================================================================
greek:
description: |
Greek historical documents span Byzantine manuscripts, Ottoman-era parish
registers (often bilingual Greek/Ottoman Turkish), and modern civil records.
Names follow patronymic patterns with genitive case inflection.
Key features:
- Patronymics in genitive case (του Ιωάννη = of Ioannis)
- Byzantine titles and honorifics
- Ottoman-era Greek with Turkish administrative terms
- Greek Orthodox church terminology
source_types:
- "ληξιαρχικά βιβλία" # civil registry
- "μητρώα βαπτίσεων" # baptismal registers
- "μητρώα γάμων" # marriage registers
- "κώδικες μονών" # monastery codices
- "πατριαρχικά έγγραφα" # patriarchal documents
patterns:
# Child-parent relationships
child_of:
- "υιός του" # son of (+ genitive)
- "θυγατέρα του" # daughter of (+ genitive)
- "υιός της" # son of (female, + genitive)
- "θυγατέρα της" # daughter of (female, + genitive)
- "γιος του" # son of (modern)
- "κόρη του" # daughter of (modern)
- "τέκνον του" # child of (archaic)
- "παις του" # child of (Byzantine)
- "του" # of (genitive article, male)
- "της" # of (genitive article, female)
- "γνήσιος υιός" # legitimate son
- "γνησία θυγατέρα" # legitimate daughter
- "νόθος υιός" # illegitimate son
- "νόθη θυγατέρα" # illegitimate daughter
# Spouse relationships
spouse:
- "σύζυγος του" # spouse of (male possessor)
- "σύζυγος της" # spouse of (female possessor)
- "γυναίκα του" # wife of
- "άνδρας της" # husband of
- "ομόζυγος" # spouse (formal)
- "νυμφευθείσα με" # married to (female)
- "νυμφευθείς με" # married to (male)
- "παντρεμένη με" # married to (female, modern)
- "παντρεμένος με" # married to (male, modern)
# Widow/widower
widow:
- "χήρα του" # widow of
- "χήρος της" # widower of
- "η χήρα" # the widow
- "μακαρίτης" # the late (male, blessed)
- "μακαρίτισσα" # the late (female, blessed)
- "αείμνηστος" # of eternal memory (male)
- "αείμνηστη" # of eternal memory (female)
# Siblings
sibling:
- "αδελφός του" # brother of
- "αδελφή του" # sister of
- "ετεροθαλής αδελφός" # half-brother
- "ετεροθαλής αδελφή" # half-sister
- "ομομήτριος" # maternal half-sibling
- "ομοπάτριος" # paternal half-sibling
# Grandparents/grandchildren
grandparent:
- "παππούς" # grandfather
- "γιαγιά" # grandmother
- "πάππος" # grandfather (archaic)
- "μάμμη" # grandmother (archaic)
- "εγγονός του" # grandson of
- "εγγονή του" # granddaughter of
- "προπάππος" # great-grandfather
- "προμάμμη" # great-grandmother
# Extended family
extended:
- "θείος" # uncle
- "θεία" # aunt
- "ανιψιός" # nephew
- "ανιψιά" # niece
- "ξάδελφος" # cousin (male)
- "ξαδέλφη" # cousin (female)
- "πρωτοξάδελφος" # first cousin (male)
- "πρωτοξαδέλφη" # first cousin (female)
# In-laws
in_law:
- "πεθερός" # father-in-law
- "πεθερά" # mother-in-law
- "γαμπρός" # son-in-law / brother-in-law
- "νύφη" # daughter-in-law / bride
- "κουνιάδος" # brother-in-law
- "κουνιάδα" # sister-in-law
- "συμπέθερος" # co-father-in-law
- "συμπεθέρα" # co-mother-in-law
# Godparent relationships
godparent:
- "νονός" # godfather
- "νονά" # godmother
- "ανάδοχος" # godparent (formal)
- "βαπτιστικός" # godson
- "βαπτιστική" # goddaughter
- "κουμπάρος" # best man / godfather
- "κουμπάρα" # best woman / godmother
- "σύντεκνος" # co-parent (spiritual kinship)
# Honorifics and titles
honorifics:
- "Κύριος" # Mister / Lord
- "Κυρία" # Mrs. / Lady
- "Δεσπότης" # Bishop / Master
- "Δεσπόινα" # Lady (unmarried)
- "Άρχων" # Archon (Byzantine title)
- "Σεβαστός" # Sebastos (Byzantine title)
- "Πρωτοσπαθάριος" # Protospatharios (Byzantine)
- "Μέγας Λογοθέτης" # Grand Logothete (Byzantine)
- "Παπάς" # Priest (Orthodox)
- "Ιερεύς" # Priest (formal)
- "Διάκονος" # Deacon
- "Μοναχός" # Monk
- "Μοναχή" # Nun
- "Ηγούμενος" # Abbot
- "Ηγουμένη" # Abbess
# Deceased markers
deceased:
- "μακαρίτης" # the late (blessed, male)
- "μακαρίτισσα" # the late (blessed, female)
- "αείμνηστος" # of eternal memory (male)
- "αείμνηστη" # of eternal memory (female)
- "αποθανών" # the deceased (male)
- "αποθανούσα" # the deceased (female)
# =============================================================================
# RUSSIAN HISTORICAL PATTERNS
# =============================================================================
# Coverage: Imperial Russia, Soviet era, modern Russia
# Script: Cyrillic
# =============================================================================
russian:
description: |
Russian historical documents include metrical books (метрические книги),
revision lists (ревизские сказки), and church records. Names follow
a three-part system: given name, patronymic (отчество), and surname.
Key features:
- Patronymics formed with -ович/-евич (male) or -овна/-евна (female)
- Estate/class designations (сословие)
- Diminutive forms of given names
- Pre-revolutionary vs. Soviet-era terminology
source_types:
- "метрические книги" # metrical books (vital records)
- "ревизские сказки" # revision lists (censuses)
- "исповедные росписи" # confession lists
- "клировые ведомости" # clerical records
- "формулярные списки" # service records
- "родословные книги" # genealogical books
patterns:
# Child-parent relationships
child_of:
- "сын" # son
- "дочь" # daughter
- "сын крестьянина" # son of a peasant
- "дочь мещанина" # daughter of a townsman
- "законный сын" # legitimate son
- "законная дочь" # legitimate daughter
- "незаконнорождённый" # illegitimate (male)
- "незаконнорождённая" # illegitimate (female)
- "приёмный сын" # adopted son
- "приёмная дочь" # adopted daughter
- "воспитанник" # foster child (male)
- "воспитанница" # foster child (female)
# Patronymic patterns
patronymic:
- "-ович" # male patronymic suffix (after consonant)
- "-евич" # male patronymic suffix (after vowel/soft consonant)
- "-ич" # male patronymic suffix (short form)
- "-овна" # female patronymic suffix (after consonant)
- "-евна" # female patronymic suffix (after vowel/soft consonant)
- "-ична" # female patronymic suffix (archaic)
- "-инична" # female patronymic suffix (archaic variant)
# Spouse relationships
spouse:
- "жена" # wife
- "муж" # husband
- "супруга" # spouse (female)
- "супруг" # spouse (male)
- "законная жена" # lawful wife
- "законный муж" # lawful husband
- "венчаная жена" # church-married wife
- "венчаный муж" # church-married husband
# Widow/widower
widow:
- "вдова" # widow
- "вдовец" # widower
- "вдова после" # widow of (+ genitive)
- "покойный" # the late (male)
- "покойная" # the late (female)
- "умерший" # the deceased (male)
- "умершая" # the deceased (female)
- "в Бозе почивший" # resting in God (male, religious)
- "в Бозе почившая" # resting in God (female, religious)
# Siblings
sibling:
- "брат" # brother
- "сестра" # sister
- "родной брат" # full brother
- "родная сестра" # full sister
- "единоутробный брат" # maternal half-brother
- "единоутробная сестра" # maternal half-sister
- "единокровный брат" # paternal half-brother
- "единокровная сестра" # paternal half-sister
- "сводный брат" # stepbrother
- "сводная сестра" # stepsister
# Grandparents/grandchildren
grandparent:
- "дед" # grandfather
- "бабка" # grandmother (archaic)
- "бабушка" # grandmother
- "дедушка" # grandfather (affectionate)
- "внук" # grandson
- "внучка" # granddaughter
- "прадед" # great-grandfather
- "прабабка" # great-grandmother
- "правнук" # great-grandson
- "правнучка" # great-granddaughter
# Extended family
extended:
- "дядя" # uncle
- "тётя" # aunt
- "тётка" # aunt (archaic)
- "племянник" # nephew
- "племянница" # niece
- "двоюродный брат" # first cousin (male)
- "двоюродная сестра" # first cousin (female)
- "троюродный брат" # second cousin (male)
- "троюродная сестра" # second cousin (female)
# In-laws
in_law:
- "тесть" # father-in-law (wife's father)
- "тёща" # mother-in-law (wife's mother)
- "свёкор" # father-in-law (husband's father)
- "свекровь" # mother-in-law (husband's mother)
- "зять" # son-in-law
- "невестка" # daughter-in-law
- "сноха" # daughter-in-law (son's wife)
- "деверь" # husband's brother
- "золовка" # husband's sister
- "шурин" # wife's brother
- "свояченица" # wife's sister
- "свояк" # sister's husband
# Godparent relationships
godparent:
- "крёстный отец" # godfather
- "крёстная мать" # godmother
- "крёстный" # godfather (short)
- "крёстная" # godmother (short)
- "крестник" # godson
- "крестница" # goddaughter
- "кум" # co-father (spiritual kinship)
- "кума" # co-mother (spiritual kinship)
- "восприемник" # godparent (formal, male)
- "восприемница" # godparent (formal, female)
# Estate/class designations (сословия)
estate:
- "дворянин" # nobleman
- "дворянка" # noblewoman
- "потомственный дворянин" # hereditary nobleman
- "личный дворянин" # personal nobleman
- "купец" # merchant
- "купчиха" # merchant's wife
- "мещанин" # townsman
- "мещанка" # townswoman
- "крестьянин" # peasant
- "крестьянка" # peasant woman
- "однодворец" # single-homesteader
- "казак" # Cossack
- "казачка" # Cossack woman
- "разночинец" # person of mixed estate
- "священник" # priest
- "дьякон" # deacon
- "дьячок" # sexton
- "пономарь" # acolyte
# Honorifics and titles
honorifics:
- "господин" # Mister / Sir
- "госпожа" # Mrs. / Madam
- "Его Превосходительство" # His Excellency
- "Её Превосходительство" # Her Excellency
- "Его Сиятельство" # His Highness (for counts)
- "Её Сиятельство" # Her Highness
- "князь" # prince
- "княгиня" # princess
- "граф" # count
- "графиня" # countess
- "барон" # baron
- "баронесса" # baroness
- "отец" # Father (priest)
- "батюшка" # Father (priest, affectionate)
- "матушка" # Mother (priest's wife)
# Deceased markers
deceased:
- "покойный" # the late (male)
- "покойная" # the late (female)
- "умерший" # deceased (male)
- "умершая" # deceased (female)
- "скончавшийся" # passed away (male)
- "скончавшаяся" # passed away (female)
- "в Бозе почивший" # resting in God (male)
- "в Бозе почившая" # resting in God (female)
- "приснопамятный" # of blessed memory (male)
- "приснопамятная" # of blessed memory (female)
# =============================================================================
# END OF MODULE
# =============================================================================