Triple
T5428121
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bobby Allison |
E121413
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object | Bonnie Allison |
E523704
|
NE 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: Bonnie Allison | Statement: [Bobby Allison, relative, Bonnie Allison]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bonnie Allison Context triple: [Bobby Allison, relative, Bonnie Allison]
-
A.
Bonnie Allison
chosen
Bonnie Allison is a race car driver associated with the famed Alabama Gang, a prominent group in American stock car racing.
-
B.
Bonnie Owens
Bonnie Owens was an American country music singer and songwriter known for her work in the Bakersfield sound and her collaborations with Merle Haggard and Buck Owens.
-
C.
Bonnie Lee
Bonnie Lee is the spirited and independent showgirl portrayed by Jean Arthur in the 1939 adventure film "Only Angels Have Wings."
-
D.
Bonnie Curtis
Bonnie Curtis is an American film producer known for her longtime collaboration with Steven Spielberg on movies such as "Saving Private Ryan" and "Minority Report."
-
E.
Bonnie Arnold
Bonnie Arnold is an American film producer best known for her work on pioneering computer-animated features such as Toy Story and the How to Train Your Dragon series.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69bd463c65f0819082ee6483ab4b466a |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd881998308190a071af0fe44997bc |
completed | March 20, 2026, 5:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf77af7f0881908fad92962a2a6191 |
completed | March 22, 2026, 5:01 a.m. |
Created at: March 20, 2026, 2:06 p.m.