Triple
T26634731
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jeanne du Barry (2023 film) |
E668603
|
entity |
| Predicate | festivalOpeningFilm |
P88814
|
FINISHED |
| Object | 2023 Cannes Film Festival |
—
|
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: 2023 Cannes Film Festival | Statement: [Jeanne du Barry (2023 film), festivalOpeningFilm, 2023 Cannes Film Festival]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: festivalOpeningFilm Context triple: [Jeanne du Barry (2023 film), festivalOpeningFilm, 2023 Cannes Film Festival]
-
A.
festivalPremiereDate
Indicates the date on which a work (such as a film) first premieres at a festival.
-
B.
opensFilm
chosen
Indicates that one entity is the opening film of another entity, such as a festival, series, or program.
-
C.
filmFestivalScreening
Indicates that a film is being shown or presented as part of the official program of a film festival.
-
D.
festivalFeature
Indicates that a festival includes or showcases a particular element, activity, or attraction as one of its features.
-
E.
filmFestivalPremiereYear
Indicates the year in which a film first premiered at a film festival.
- 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_69ee9d0024b8819090a7c8cf669a3b6c |
completed | April 26, 2026, 11:17 p.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, 2:26 a.m.