Triple
T38625509
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | What a Way to Go! |
E936993
|
entity |
| Predicate | leadActorForCharacter Louisa May Foster |
P183760
|
FINISHED |
| Object | Shirley MacLaine |
—
|
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: Shirley MacLaine | Statement: [What a Way to Go!, leadActorForCharacter Louisa May Foster, Shirley MacLaine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: leadActorForCharacter Louisa May Foster Context triple: [What a Way to Go!, leadActorForCharacter Louisa May Foster, Shirley MacLaine]
-
A.
leadActressCharacterName
Indicates the name of the character portrayed by the lead actress in a given work.
-
B.
leadActressPlaysCharacter
chosen
Indicates that a lead actress portrays or performs the role of a specific character.
-
C.
filmLeadCharacter
Indicates that a person or character serves as the primary or central protagonist in a film.
-
D.
leadRoleActor
Indicates that an actor performs a leading or principal role in a work or production.
-
E.
directorCharacterOf
Indicates that a director is responsible for directing a particular character in a work (e.g., film, TV show, or play).
- 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_69f76ed403208190b862dc795171353f |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fcf36d2894819089b7db8e91b63c9d |
completed | May 7, 2026, 8:17 p.m. |
| PD | Predicate disambiguation | batch_69fcf25c0a108190bfa823474098640b |
completed | May 7, 2026, 8:13 p.m. |
Created at: May 3, 2026, 4:32 p.m.