Triple

T33464872
Position Surface form Disambiguated ID Type / Status
Subject Joe Gargery E857017 entity
Predicate treatmentBySpouse P51768 FINISHED
Object is abused by Mrs. Joe Gargery 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: is abused by Mrs. Joe Gargery | Statement: [Joe Gargery, treatmentBySpouse, is abused by Mrs. Joe Gargery]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: treatmentBySpouse
Context triple: [Joe Gargery, treatmentBySpouse, is abused by Mrs. Joe Gargery]
  • A. throughSpouse
    Indicates a relationship or connection that exists indirectly between two entities by way of one entity’s spouse.
  • B. spouseAction chosen
    Indicates that one person performs an action toward or on their spouse within the context of a marital relationship.
  • C. spouse
    Indicates that two entities are married to each other in a legally or socially recognized partnership.
  • D. spouseInvolvedIn
    Indicates that a person's spouse participates in, is associated with, or plays a role in a specified activity, event, or situation.
  • E. governedThroughSpouse
    Indicates that one entity exercised governing authority or political power indirectly through their spouse, who held the formal ruling position.
  • 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_69f34973461481909c701c98ebd75623 completed April 30, 2026, 12:22 p.m.
NER Named-entity recognition batch_69f7308a096081909d66a56f3c926806 completed May 3, 2026, 11:24 a.m.
PD Predicate disambiguation batch_69f72a00c5f081908b6539d15baf4e12 completed May 3, 2026, 10:57 a.m.
Created at: May 1, 2026, 1:37 a.m.