Triple
T25167112
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | James Stevens |
E630208
|
entity |
| Predicate | filmScreenwriterOfAdaptation |
P23410
|
FINISHED |
| Object | Ruth Prawer Jhabvala |
—
|
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: Ruth Prawer Jhabvala | Statement: [James Stevens, filmScreenwriterOfAdaptation, Ruth Prawer Jhabvala]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: filmScreenwriterOfAdaptation Context triple: [James Stevens, filmScreenwriterOfAdaptation, Ruth Prawer Jhabvala]
-
A.
screenWriterAdaptationBy
chosen
Indicates that a person served as the screenwriter responsible for adapting an existing work into a screenplay.
-
B.
adaptedForFilmBy
Indicates that a work has been turned into a film by a particular person or entity responsible for the adaptation.
-
C.
screenwriterOfWorkAppearingIn
Indicates that a person is the screenwriter of a work in which a specified entity (such as a character, actor, or role) appears.
-
D.
filmWriterOfWork
Indicates that a person is the writer or screenwriter responsible for creating the script or written content of a particular film.
-
E.
screenwriterOfWork
Indicates that a person served as the screenwriter (wrote the screenplay) for a particular creative 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_69e75a87c9b88190ab60731902a99750 |
completed | April 21, 2026, 11:07 a.m. |
| NER | Named-entity recognition | batch_69f46d42ec0081908231beebf495cf3e |
completed | May 1, 2026, 9:07 a.m. |
| PD | Predicate disambiguation | batch_69f44d8043b081908bbffd7f044b4f26 |
completed | May 1, 2026, 6:51 a.m. |
Created at: April 21, 2026, 12:17 p.m.