Triple
T23911190
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Big Sleep (1978 film) |
E601941
|
entity |
| Predicate | hasEarlierFilmAdaptation |
P104372
|
FINISHED |
| Object | The Big Sleep (1946 film) |
—
|
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: The Big Sleep (1946 film) | Statement: [The Big Sleep (1978 film), hasEarlierFilmAdaptation, The Big Sleep (1946 film)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasEarlierFilmAdaptation Context triple: [The Big Sleep (1978 film), hasEarlierFilmAdaptation, The Big Sleep (1946 film)]
-
A.
hasPreviousFilmAdaptation
Indicates that a work has been adapted into a film before the current or referenced adaptation.
-
B.
precededByFilmAdaptationOfSameNovel
chosen
Indicates that the subject film was released after, and is chronologically preceded by, another film adaptation of the same source novel.
-
C.
hasGraphicNovelAdaptation
Indicates that a work has been adapted into a graphic novel format.
-
D.
isTelevisionAdaptationOf
Indicates that a television show is an adaptation derived from the story, characters, or content of another original work.
-
E.
previousFilmAdaptationOfSamePlay
Indicates that one film is an earlier screen adaptation of the same underlying play as another film.
- 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_69e2953a187081908346a9f36e85fc98 |
completed | April 17, 2026, 8:16 p.m. |
| NER | Named-entity recognition | batch_69f1ce94f65c8190807723344fa0b837 |
completed | April 29, 2026, 9:25 a.m. |
| PD | Predicate disambiguation | batch_69f16151ebdc819086e9e1d7cc1f4f3c |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:38 p.m.