Triple
T37109497
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Isle of Dogs (2018 film) |
E918944
|
entity |
| Predicate | berlinFilmFestivalAward |
P128344
|
FINISHED |
| Object | Silver Bear for Best Director |
—
|
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: Silver Bear for Best Director | Statement: [Isle of Dogs (2018 film), berlinFilmFestivalAward, Silver Bear for Best Director]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: berlinFilmFestivalAward Context triple: [Isle of Dogs (2018 film), berlinFilmFestivalAward, Silver Bear for Best Director]
-
A.
cannesFilmFestivalAward
Indicates that an entity has received an award presented at the Cannes Film Festival.
-
B.
awardFestival
chosen
Indicates that an entity receives or is granted an award in the context of a festival or festival-related event.
-
C.
filmFestivalAwardedAt
Indicates that a particular film festival award was given or presented at a specific film festival event or edition.
-
D.
bestForeignLanguageFilmWinner
Indicates that the subject is the film that won the award for Best Foreign Language Film in the specified context or event.
-
E.
bestAssistantDirectorWinnerFilm
Indicates that a film is the work for which a particular assistant director won the Best Assistant Director award.
- 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_69f76e9b99c8819096164b21ff5bd996 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb344c60f8819090f2e21e1e61d621 |
completed | May 6, 2026, 12:30 p.m. |
| PD | Predicate disambiguation | batch_69fb2f642db08190b562725502c74ea6 |
completed | May 6, 2026, 12:09 p.m. |
Created at: May 3, 2026, 4:14 p.m.