Triple
T34348630
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Academy Award for Best Picture (as producer of Saving Private Ryan) |
E881504
|
entity |
| Predicate | competingFilm |
P188817
|
FINISHED |
| Object | Shakespeare in Love |
—
|
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: Shakespeare in Love | Statement: [Academy Award for Best Picture (as producer of Saving Private Ryan), competingFilm, Shakespeare in Love]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: competingFilm Context triple: [Academy Award for Best Picture (as producer of Saving Private Ryan), competingFilm, Shakespeare in Love]
-
A.
competingCinema
Indicates that two cinema entities are in competition with each other, typically for the same audience or market.
-
B.
hasRivalInFilm
Indicates that one entity serves as a rival or adversary to another within the context of a specific film.
-
C.
filmCounterpart
Indicates that one entity is the film version or adaptation counterpart of another entity from a different medium (such as a book, game, or TV series).
-
D.
distributedFilm
Indicates that one entity served as the distributor responsible for releasing or circulating a particular film.
-
E.
alsoFilmedIn
Indicates that the same film or video production was additionally shot or recorded in another specified location.
- F. None of above. chosen
Provenance (4 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_69f349bc55e881908c8e338ef76b0043 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69fbad1e94988190b86d447a68e65067 |
completed | May 6, 2026, 9:05 p.m. |
| PD | Predicate disambiguation | batch_69fba881b8e0819094790935152b99a1 |
completed | May 6, 2026, 8:45 p.m. |
| PDg | Predicate description generation | batch_69fbad1b3ba08190ad69e21461333f2e |
completed | May 6, 2026, 9:05 p.m. |
Created at: May 1, 2026, 1:58 a.m.