Triple
T7379551
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Marrying Man |
E170211
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | David Permut |
E166456
|
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: David Permut | Statement: [The Marrying Man, producer, David Permut]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: David Permut Context triple: [The Marrying Man, producer, David Permut]
-
A.
David Permut
chosen
David Permut is an American film producer known for working on a wide range of Hollywood movies, including both studio comedies and independent dramas.
-
B.
Gregory Perler
Gregory Perler is a film editor best known for his work on major animated features, including the movie "Rio 2."
-
C.
Perry Johanson
Perry Johanson was an American architect best known as one of the founding partners of the global architecture and design firm NBBJ.
-
D.
Ben L. Perry
Ben L. Perry was a screenwriter best known for his work on mid-20th-century American genre films, including the Western noir "Terror in a Texas Town."
-
E.
Brandon Perlman
Brandon Perlman is the son of American actor Ron Perlman and works as a music producer and DJ.
- 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_69c68a5d0ed08190b6d361e68f813330 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f1c61484819087874d4e7f9fd791 |
completed | March 27, 2026, 9:08 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c802d86da48190a1311c5c52a5f296 |
completed | March 28, 2026, 4:33 p.m. |
Created at: March 27, 2026, 3:08 p.m.