Triple
T33853293
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Keith Gordon as Peter Miller |
E867692
|
entity |
| Predicate | workHasDirector |
P107822
|
FINISHED |
| Object | Brian De Palma |
—
|
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: Brian De Palma | Statement: [Keith Gordon as Peter Miller, workHasDirector, Brian De Palma]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: workHasDirector Context triple: [Keith Gordon as Peter Miller, workHasDirector, Brian De Palma]
-
A.
hasDirectorOfWork
Indicates that an entity has a specific person or organization serving as the director responsible for overseeing its work or project.
-
B.
hasDirectorInKeyWork
Indicates that a director is associated with a key or primary work of an entity (such as a film, series, or major production).
-
C.
workOfDirector
chosen
Indicates that a creative work (such as a film, play, or show) is directed by a particular director.
-
D.
workOfDirectorKnownFor
Indicates that a work (such as a film or show) is directed by a person for whom this work is one of their notable or best-known creations.
-
E.
hasDirectorStar
Indicates that a person both directed and starred in the same work (e.g., film, show, or production).
- F. None of above.
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_69f349937b648190a34ada70f6a2b534 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f70075a0888190b3470cf7e5aaf482 |
completed | May 3, 2026, 7:59 a.m. |
| PD | Predicate disambiguation | batch_69f6fc59518081908b0275f47721d561 |
completed | May 3, 2026, 7:42 a.m. |
Created at: May 1, 2026, 1:47 a.m.