Triple
T10193307
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ʿĀtika bint Abd al-Muttalib |
E238092
|
entity |
| Predicate | hasKinshipRole |
P38221
|
FINISHED |
| Object | aunt of the Prophet Muhammad |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: aunt of the Prophet Muhammad | Statement: [ʿĀtika bint Abd al-Muttalib, hasKinshipRole, aunt of the Prophet Muhammad]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasKinshipRole Context triple: [ʿĀtika bint Abd al-Muttalib, hasKinshipRole, aunt of the Prophet Muhammad]
-
A.
hasFamilyRole
chosen
Indicates that one entity holds a specific familial role or position in relation to another entity.
-
B.
usesKinshipSystem
Indicates that one entity organizes or interprets familial relationships according to the kinship classification system associated with another entity.
-
C.
hasFamilialTieTo
Indicates a relationship where two entities are connected by family bonds, such as by blood, marriage, or adoption.
-
D.
hasGenealogicalRelation
Indicates that there exists a family or ancestry-based relationship (such as parent, child, sibling, or more distant kinship) between the related entities.
-
E.
hasFamilyRelationContext
Indicates that there exists a family-based relationship or kinship context connecting the referenced entities.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69ca84de1b208190bf17bb305b002605 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdedc675008190b8248325f5a208bf |
completed | April 2, 2026, 4:17 a.m. |
| PD | Predicate disambiguation | batch_69cd7c8477648190bc55c56aeec507d3 |
completed | April 1, 2026, 8:13 p.m. |
Created at: March 30, 2026, 9:13 p.m.