Triple
T22425593
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Just Cause |
E554359
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object | Arne Glimcher |
—
|
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: Arne Glimcher | Statement: [Just Cause, director, Arne Glimcher]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Arne Glimcher Context triple: [Just Cause, director, Arne Glimcher]
-
A.
Arne Glimcher
chosen
Arne Glimcher is an American art dealer, film producer, and director best known as the founder of the Pace Gallery and for directing the film adaptation of "The Mambo Kings."
-
B.
Robert Kravis
Robert Kravis is a film producer best known for his work on the crime thriller "Lucky Number Slevin."
-
C.
Andrew Weill
Andrew Weill is an individual notable enough to be recognized as a namesake of the surname Weill, though specific widely known public details about him are not clearly established.
-
D.
Joel Rosenman
Joel Rosenman is an American lawyer, entrepreneur, and music producer best known as one of the principal backers and co-creators of the 1969 Woodstock music festival.
-
E.
Robert S. Taubman
Robert S. Taubman is an American real estate executive best known for leading the Taubman Company, a major developer and operator of shopping malls.
- 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_69e11e4f2d0c819091aa3558ea2ee630 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15a2d4dd88190a156c24b02b1591b |
completed | April 29, 2026, 1:09 a.m. |
Created at: April 16, 2026, 8:47 p.m.