Triple
T28996227
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andrew Dosunmu |
E736168
|
entity |
| Predicate | filmPremieredAt |
P144121
|
FINISHED |
| Object | Sundance Film Festival |
—
|
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: Sundance Film Festival | Statement: [Andrew Dosunmu, filmPremieredAt, Sundance Film Festival]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: filmPremieredAt Context triple: [Andrew Dosunmu, filmPremieredAt, Sundance Film Festival]
-
A.
filmFestivalPremiereYear
Indicates the year in which a film first premiered at a film festival.
-
B.
festivalPremiereDate
Indicates the date on which a work (such as a film) first premieres at a festival.
-
C.
filmRelease
chosen
Indicates the event or relationship in which a film is made publicly available, typically specifying when, where, or how it is released.
-
D.
sectionPremieredIn
Indicates that a specific section or part of a work first premiered or was initially presented in a particular event, venue, or context.
-
E.
premieredInProduction
Indicates that a work (such as a play, film, or performance) had its first public showing or debut in a specific production.
- 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_69f077eacd0481908ef0bafd74491cd0 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69f65fb599c08190aac2f24dda602f72 |
completed | May 2, 2026, 8:33 p.m. |
| PD | Predicate disambiguation | batch_69f659d02f1c8190831758ac52bb54e4 |
completed | May 2, 2026, 8:08 p.m. |
Created at: April 28, 2026, 9:31 a.m.