Triple
T36784100
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cher as Rusty Dennis |
E908852
|
entity |
| Predicate | castingChoiceReason |
P52446
|
FINISHED |
| Object | Cher’s dramatic acting ability |
—
|
LITERAL FINISHED |
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: Cher’s dramatic acting ability | Statement: [Cher as Rusty Dennis, castingChoiceReason, Cher’s dramatic acting ability]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: castingChoiceReason Context triple: [Cher as Rusty Dennis, castingChoiceReason, Cher’s dramatic acting ability]
-
A.
castingReason
chosen
Indicates the reason or justification for selecting or assigning a particular entity (e.g., a person or object) to a specific role, function, or category.
-
B.
castingChoiceFor
Indicates a relationship where a particular casting decision or option is selected or designated for a specific role, production, or performance.
-
C.
selectionReason
Indicates the reason or justification for choosing or selecting one entity over alternatives.
-
D.
madeChoiceBetween
Indicates that an entity selected one option from among two or more specified alternatives.
-
E.
castingVote
Indicates that an entity formally expresses a decisive choice or preference in a vote, often determining the outcome.
- 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_69f76e7a937c81909ed7359641e670f6 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f7ca93bd0481909d6eee9e950001a1 |
completed | May 3, 2026, 10:22 p.m. |
| PD | Predicate disambiguation | batch_69f7c89b528c8190bf80b230fc7c7108 |
completed | May 3, 2026, 10:13 p.m. |
Created at: May 3, 2026, 4:12 p.m.