Triple
T26701158
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gene Hackman as Little Bill Daggett |
E673157
|
entity |
| Predicate | editorOfFilm |
P14416
|
FINISHED |
| Object | Joel Cox |
—
|
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: Joel Cox | Statement: [Gene Hackman as Little Bill Daggett, editorOfFilm, Joel Cox]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: editorOfFilm Context triple: [Gene Hackman as Little Bill Daggett, editorOfFilm, Joel Cox]
-
A.
editedFilmForDirector
Indicates that one person performed film editing work on a movie under the direction or supervision of a specific director.
-
B.
director
Indicates that one entity serves as the director (creative or managerial leader) of another entity, such as a film, organization, or project.
-
C.
editedFilm
chosen
Indicates that one entity performed the film editing work on another entity, which is a film.
-
D.
filmEditingNominee
Indicates that an entity was nominated for an award recognizing excellence in film editing for a particular film or work.
-
E.
studioFilm
Indicates that a film is produced, distributed, or otherwise created by a particular studio.
- 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_69eecda2b49c8190a6c481cfc4c07954 |
completed | April 27, 2026, 2:44 a.m. |
| NER | Named-entity recognition | batch_69f621fcea1481909b6f8b3af1ee6820 |
completed | May 2, 2026, 4:10 p.m. |
| PD | Predicate disambiguation | batch_69f620debeb48190b7db395fb86cf8d9 |
completed | May 2, 2026, 4:05 p.m. |
Created at: April 27, 2026, 3:31 a.m.