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.