Triple
T35820209
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Art of Racing in the Rain |
E1035476
|
entity |
| Predicate | voiceActorOfEnzo |
P184201
|
FINISHED |
| Object | Kevin Costner |
—
|
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: Kevin Costner | Statement: [The Art of Racing in the Rain, voiceActorOfEnzo, Kevin Costner]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: voiceActorOfEnzo Context triple: [The Art of Racing in the Rain, voiceActorOfEnzo, Kevin Costner]
-
A.
voiceActorForSebastian
Indicates that one entity serves as the voice actor who provides the spoken performance for the character Sebastian in a work.
-
B.
voiceActorOfTom
Indicates that one entity serves as the voice actor for the character or role associated with Tom.
-
C.
voiceTypeOfEnrico
Indicates that the specified voice type is the vocal classification associated with Enrico.
-
D.
voiceActorForEd
Indicates that one entity serves as the voice actor for the character or role named Ed.
-
E.
voiceActorForMario
Indicates that one entity serves as the voice actor who provides the spoken or vocal performance for the character Mario in a work or series of works.
- 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_69f76e185ffc8190880b3cdf51decd38 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7acaec1508190a38f2ac9cc5383e7 |
completed | May 3, 2026, 8:14 p.m. |
| PD | Predicate disambiguation | batch_69f7ab734d848190a84f9b8c3a952b75 |
completed | May 3, 2026, 8:09 p.m. |
| PDg | Predicate description generation | batch_69f7ac2210e481909279dade5328825c |
completed | May 3, 2026, 8:12 p.m. |
Created at: May 3, 2026, 4:06 p.m.