Triple
T10537128
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alan Jay Lerner |
E248595
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Michele Lerner |
E248595
|
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: Michele Lerner | Statement: [Alan Jay Lerner, spouse, Michele Lerner]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michele Lerner Context triple: [Alan Jay Lerner, spouse, Michele Lerner]
-
A.
Michele Lerner
chosen
Michele Lerner is known primarily as the third wife of American lyricist and playwright Alan Jay Lerner.
-
B.
George Lerner
George Lerner was an American toy inventor best known for creating the iconic Mr. Potato Head character.
-
C.
Michael Lerner
Michael Lerner was an American character actor known for his prolific film and television career, including an Academy Award–nominated role in "Barton Fink."
-
D.
Murray Lerner
Murray Lerner was an American documentary and concert filmmaker best known for his music films capturing iconic performances by artists such as Bob Dylan, Jimi Hendrix, and The Who.
-
E.
Jeffrey Lerner
Jeffrey Lerner is a film and television producer known for his work as an executive producer on various projects, including the movie "Watch Over Me."
- 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_69d381c5c7448190bec34bee7ec72bac |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d50a554fb4819081e9618bab051dc6 |
completed | April 7, 2026, 1:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f4578899ac81908b6e3c8948ca6628 |
completed | May 1, 2026, 7:34 a.m. |
Created at: April 6, 2026, 12:31 p.m.