Triple
T25194665
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oblivion Song |
E630968
|
entity |
| Predicate | filmAdaptationRole |
P114853
|
FINISHED |
| Object | Jake Gyllenhaal attached to star as Nathan Cole |
—
|
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: Jake Gyllenhaal attached to star as Nathan Cole | Statement: [Oblivion Song, filmAdaptationRole, Jake Gyllenhaal attached to star as Nathan Cole]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: filmAdaptationRole Context triple: [Oblivion Song, filmAdaptationRole, Jake Gyllenhaal attached to star as Nathan Cole]
-
A.
filmAdaptationStarred
chosen
Indicates that a particular person played a starring role in a specific film adaptation of a work.
-
B.
filmAdaptationEvaPerformer
Indicates that the subject is a performer who played the character Eva in a film adaptation of the referenced work.
-
C.
filmAdaptationDirectorAttached
Indicates that a specific director is officially attached to direct a planned or in-development film adaptation of a work.
-
D.
adaptedIntoFilmStarring
Indicates that a work has been adapted into a film in which a specified actor or set of actors star.
-
E.
filmAdaptationOfWork
Indicates that a film is an adaptation based on the narrative content of a specific original work.
- 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_69e75a8a6d088190ba1e82a4345225e7 |
completed | April 21, 2026, 11:07 a.m. |
| NER | Named-entity recognition | batch_69f46e1206f88190bfacdc420027c354 |
completed | May 1, 2026, 9:10 a.m. |
| PD | Predicate disambiguation | batch_69f4683472ec8190a483b3b8afe71720 |
completed | May 1, 2026, 8:45 a.m. |
Created at: April 21, 2026, 12:46 p.m.