Triple

T36668576
Position Surface form Disambiguated ID Type / Status
Subject Tulip O’Hare E905340 entity
Predicate exGirlfriendOf P96926 FINISHED
Object Jesse Custer NE NERFINISHED

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: Jesse Custer | Statement: [Tulip O’Hare, exGirlfriendOf, Jesse Custer]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: exGirlfriendOf
Context triple: [Tulip O’Hare, exGirlfriendOf, Jesse Custer]
  • A. exGirlfriend chosen
    Indicates that one person was previously in a romantic relationship as a girlfriend of another person, but that relationship has since ended.
  • B. exBoyfriendOf
    Indicates that one person was formerly the romantic boyfriend of another person.
  • C. hasBoyfriend
    Indicates that a person is in a romantic relationship where the other party is their boyfriend.
  • D. femalePartner
    Indicates that one entity is the female partner in a romantic or marital relationship with the other entity.
  • E. formerRomanticInterest
    Indicates that one entity previously had a romantic relationship or attraction toward another entity, but that romantic connection has since ended.
  • 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_69f76e6f10008190aea41746aa1b186e completed May 3, 2026, 3:49 p.m.
NER Named-entity recognition batch_69f7c79cf5a48190a0f56db1d77e8419 completed May 3, 2026, 10:09 p.m.
PD Predicate disambiguation batch_69f7c4796ebc819084a0dc08505e5f14 completed May 3, 2026, 9:56 p.m.
Created at: May 3, 2026, 4:12 p.m.