Triple
T34126002
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Age of Innocence (1993 film) |
E875277
|
entity |
| Predicate | hasSupportingActressNominee |
P31998
|
FINISHED |
| Object | Winona Ryder |
—
|
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: Winona Ryder | Statement: [The Age of Innocence (1993 film), hasSupportingActressNominee, Winona Ryder]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSupportingActressNominee Context triple: [The Age of Innocence (1993 film), hasSupportingActressNominee, Winona Ryder]
-
A.
supportingActressNominee
chosen
Indicates that a person has been nominated for an award in the category of supporting actress.
-
B.
supportingActorNominee
Indicates that an entity has been nominated for an award recognizing their performance in a supporting acting role.
-
C.
leadingActressNominee
Indicates that a person has been nominated for an award in the leading actress category for a particular work or performance.
-
D.
supportingActorAwardRecipient
Indicates that an entity has received an award specifically for a supporting acting role in a performance or production.
-
E.
screenActorsGuildAwardNominee
Indicates that an entity has been nominated for a Screen Actors Guild 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_69f349aa33848190a2e6c5e4533c8444 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69ff84202eb081908ae21a54a4414d68 |
completed | May 9, 2026, 6:59 p.m. |
| PD | Predicate disambiguation | batch_69ff833065e4819098579129d4ee17d3 |
completed | May 9, 2026, 6:55 p.m. |
Created at: May 1, 2026, 1:53 a.m.