Triple
T7561299
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Run All Night |
E178799
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Michael Tadross |
E540789
|
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: Michael Tadross | Statement: [Run All Night, producer, Michael Tadross]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Tadross Context triple: [Run All Night, producer, Michael Tadross]
-
A.
Michael Tadross
chosen
Michael Tadross is an American film producer known for working on major Hollywood productions, including big-budget action and fantasy films.
-
B.
Jeffrey Stott
Jeffrey Stott is a film producer best known for his work on the political comedy film "The American President."
-
C.
Paul Torday
Paul Torday was a British novelist best known for his satirical debut novel "Salmon Fishing in the Yemen," which brought him widespread recognition later in life.
-
D.
Jeffrey S. Mearns
Jeffrey S. Mearns is an American academic leader and attorney who serves as the president of Ball State University in Indiana.
-
E.
Andrew D. Martin
Andrew D. Martin is an American political scientist and academic administrator who serves as the chancellor of Washington University in St. Louis.
- 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_69c69f2f80288190b95cceb4da92ab2b |
completed | March 27, 2026, 3:15 p.m. |
| NER | Named-entity recognition | batch_69c6f8f847c48190a1081aa9de7ff945 |
completed | March 27, 2026, 9:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c856d0cbfc8190b2cb2b601a7b078c |
completed | March 28, 2026, 10:31 p.m. |
Created at: March 27, 2026, 3:50 p.m.