Triple
T38350050
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cannes Film Festival Special 60th Anniversary Prize |
E1041654
|
entity |
| Predicate | editionOfFestival |
P35011
|
FINISHED |
| Object | 2007 Cannes 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: 2007 Cannes Film Festival | Statement: [Cannes Film Festival Special 60th Anniversary Prize, editionOfFestival, 2007 Cannes Film Festival]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: editionOfFestival Context triple: [Cannes Film Festival Special 60th Anniversary Prize, editionOfFestival, 2007 Cannes Film Festival]
-
A.
festivalEditionYear
Indicates the specific calendar year in which a particular edition of a recurring festival takes place.
-
B.
eventEditionNumber
Indicates the ordinal number assigned to a specific edition or occurrence of a recurring event.
-
C.
editionHeldIn
Indicates that a particular edition of a work is physically or digitally held or housed in a specific location or institution.
-
D.
editionOfCompetition
chosen
Indicates that one entity is a specific edition or iteration of a recurring competition or tournament.
-
E.
editionNumber
Indicates the specific sequential number assigned to an edition of a work within its series of published versions.
- 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_69f76e2ad95481908c920c0e5c1c3e26 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fcc7a4d7f881908b43b960911b81e9 |
completed | May 7, 2026, 5:11 p.m. |
| PD | Predicate disambiguation | batch_69fcc589720c819089c8f500fea3c86a |
completed | May 7, 2026, 5:02 p.m. |
Created at: May 3, 2026, 4:30 p.m.