Triple
T8625789
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Le Mépris |
E204276
|
entity |
| Predicate | featuresFilmWithinFilm |
P51564
|
FINISHED |
| Object | adaptation of The Odyssey |
—
|
LITERAL FINISHED |
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: adaptation of The Odyssey | Statement: [Le Mépris, featuresFilmWithinFilm, adaptation of The Odyssey]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresFilmWithinFilm Context triple: [Le Mépris, featuresFilmWithinFilm, adaptation of The Odyssey]
-
A.
filmWithinFilm
chosen
Indicates that one film is depicted, referenced, or shown as existing within the narrative of another film.
-
B.
filmicFunction
Indicates the role or purpose that something serves within the structure, style, or narrative function of a film.
-
C.
filmBase
Indicates the primary location or headquarters from which a film-related entity (such as a production, company, or operation) is based or operates.
-
D.
includedInFilm
Indicates that one entity (such as a scene, segment, or element) is contained within or forms part of a particular film.
-
E.
basedInFilm
Indicates that something (such as a character, event, or work) is situated, set, or primarily located within the context or universe of a particular 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_69ca834a4ea0819094970dceb9e389f3 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc5730309081909a9a0256c9bf5f8f |
completed | March 31, 2026, 11:22 p.m. |
| PD | Predicate disambiguation | batch_69cc455906f8819082edd79cb4a1cf28 |
completed | March 31, 2026, 10:06 p.m. |
Created at: March 30, 2026, 6:26 p.m.