Triple
T21798022
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chef's Table |
E538151
|
entity |
| Predicate | developer |
P73
|
FINISHED |
| Object | David Gelb |
—
|
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: David Gelb | Statement: [Chef's Table, developer, David Gelb]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: David Gelb Context triple: [Chef's Table, developer, David Gelb]
-
A.
David Gelb
chosen
David Gelb is an American filmmaker and producer best known for creating and directing the documentary "Jiro Dreams of Sushi" and for developing the Netflix series "Chef's Table."
-
B.
Don Wexler
Don Wexler was an influential American architect best known for his innovative mid-century modern steel-and-glass residential and commercial designs in Palm Springs, California.
-
C.
Edward Neumeier
Edward Neumeier is an American screenwriter and producer best known for writing the science fiction films RoboCop and Starship Troopers.
-
D.
John Scher
John Scher is an American concert promoter and music industry executive known for organizing major large-scale events and festivals, including Woodstock '94.
-
E.
Michael Steinberg
Michael Steinberg is a film producer best known for his work on the hit comedy "There's Something About Mary."
- 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_69e0c4733f4081909a86622e7e6d15d2 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f077fb87848190b6df9a9d1c5336af |
completed | April 28, 2026, 9:03 a.m. |
Created at: April 16, 2026, 6:53 p.m.