Triple
T6162091
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Get Smart |
E137465
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object | Peter Segal |
E335261
|
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: Peter Segal | Statement: [Get Smart, director, Peter Segal]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Peter Segal Context triple: [Get Smart, director, Peter Segal]
-
A.
Peter Segal
chosen
Peter Segal is an American film director known for mainstream comedies such as "Tommy Boy," "50 First Dates," and "Get Smart."
-
B.
Brett Ratner
Brett Ratner is an American film director and producer best known for commercial hits like the Rush Hour series and X-Men: The Last Stand.
-
C.
Shawn Levy
Shawn Levy is a Canadian film director, producer, and actor best known for helming mainstream comedies and adventure films such as the "Night at the Museum" series and for producing hit television shows like "Stranger Things."
-
D.
Barry Sonnenfeld
Barry Sonnenfeld is an American filmmaker and cinematographer best known for directing the Men in Black trilogy and The Addams Family films.
-
E.
David W. Zucker
David W. Zucker is a television producer known for overseeing high-profile, prestige drama series, including the adaptation of Philip K. Dick’s "The Man in the High Castle."
- 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_69c008a54fc88190b6ce4416490ca79d |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c05d371484819090c18b62b095b49e |
completed | March 22, 2026, 9:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c14199f024819089af02b1c0eebfad |
completed | March 23, 2026, 1:35 p.m. |
Created at: March 22, 2026, 4:17 p.m.