Triple
T6735985
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tom Petty |
E153755
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Jane Benyo |
E153755
|
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: Jane Benyo | Statement: [Tom Petty, spouse, Jane Benyo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jane Benyo Context triple: [Tom Petty, spouse, Jane Benyo]
-
A.
Jane Benyo
chosen
Jane Benyo is best known as the first wife of American rock musician Tom Petty, with whom she was married for over two decades.
-
B.
Vivian Oparah
Vivian Oparah is a British actress best known for her role as Tanya Adeola in the Doctor Who spin-off series "Class."
-
C.
Zaria Peterson
Zaria Peterson is a main teenage character from the sitcom "The Parent 'Hood," known as the smart and spirited daughter in the Peterson family.
-
D.
Yvonne Dereany
Yvonne Dereany is known as the wife of New Zealand politician and former Prime Minister Mike Moore.
-
E.
Jocelyn Howard
Jocelyn Howard is an American television and film actress best known as the daughter of filmmaker and former child star Ron Howard.
- 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_69c6880bdd68819097de8b6099992682 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d18369d88190a73349075462202b |
completed | March 27, 2026, 6:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c70b09b97c8190a5a538571b6909f0 |
completed | March 27, 2026, 10:56 p.m. |
Created at: March 27, 2026, 2:09 p.m.