Triple
T28012127
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shaqir O'Neal |
E707443
|
entity |
| Predicate | isChildOfCelebrity |
P37703
|
FINISHED |
| Object | Shaunie O'Neal |
—
|
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: Shaunie O'Neal | Statement: [Shaqir O'Neal, isChildOfCelebrity, Shaunie O'Neal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isChildOfCelebrity Context triple: [Shaqir O'Neal, isChildOfCelebrity, Shaunie O'Neal]
-
A.
isChildOfPublicFigure
chosen
Indicates that one person is the offspring or child of another person who is recognized as a public figure.
-
B.
parentOfCelebrity
Indicates that one entity is the parent of another entity who is a celebrity.
-
C.
isMoreFamousThan
Indicates that one entity is better known or more widely recognized by people than another entity.
-
D.
isFromFamilyKnownFor
Indicates that an entity belongs to a family that is widely recognized or notable for a particular characteristic, achievement, or reputation.
-
E.
celebrityMatch
Indicates a relationship where one entity is identified as a suitable or corresponding celebrity counterpart or pairing for another entity.
- 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_69ef96ba350c81908230d0b501b974c4 |
completed | April 27, 2026, 5:02 p.m. |
| NER | Named-entity recognition | batch_69f63fd79e4c8190af9263b679e5ff07 |
completed | May 2, 2026, 6:17 p.m. |
| PD | Predicate disambiguation | batch_69f63c6a8474819091b8c6fe98e3862d |
completed | May 2, 2026, 6:03 p.m. |
Created at: April 27, 2026, 8:04 p.m.