Triple
T22976920
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Passengers |
E571346
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Michael Maher |
—
|
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: Michael Maher | Statement: [Passengers, producer, Michael Maher]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Maher Context triple: [Passengers, producer, Michael Maher]
-
A.
Michael Maher
chosen
Michael Maher is a film producer known for his work on the movie "Passengers."
-
B.
Mike Maher
Mike Maher is an American jazz trumpeter and composer best known as a member of the genre-blending ensemble Snarky Puppy.
-
C.
Sean Maher
Sean Maher is an American actor best known for playing Dr. Simon Tam in the television series "Firefly" and its film continuation "Serenity."
-
D.
Bill Maher
Bill Maher is an American comedian, political commentator, and television host known for his satirical takes on religion and politics, particularly through his show "Real Time with Bill Maher."
-
E.
Kevin Maher
Kevin Maher is an English former professional footballer and current football manager best known for his long association with Southend United.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e245b3c50481908bb3741ec9f40862 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f182369b548190a6630655a6e0bb39 |
completed | April 29, 2026, 3:59 a.m. |
Created at: April 17, 2026, 3:48 p.m.