Triple
T3150428
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gilda Radner |
E65863
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Gilda |
E260196
|
NE 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: Gilda | Statement: [Gilda Radner, givenName, Gilda]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gilda Context triple: [Gilda Radner, givenName, Gilda]
-
A.
Gilda
chosen
Gilda is a classic 1946 American film noir starring Rita Hayworth in one of her most iconic roles.
-
B.
Johnny Guitar
Johnny Guitar is a 1954 cult-classic Western film, noted for its unconventional style, strong female lead, and subversive take on genre conventions.
-
C.
In a Lonely Place
In a Lonely Place is a 1950 film noir drama starring Humphrey Bogart as a troubled screenwriter suspected of murder, noted for its dark psychological complexity and cynical view of Hollywood and relationships.
-
D.
Lucy Gayheart
Lucy Gayheart is a 1935 novel by Willa Cather that follows a young pianist’s emotional and artistic awakening in a small Nebraska town and the tragic consequences of her romantic idealism.
-
E.
Red Dust
Red Dust is a 1932 American pre-Code romantic drama film starring Clark Gable and Jean Harlow, set on a rubber plantation in French Indochina.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ad8584485081909ed529e890cadc4a |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada5bf902c8190a490fa55e2dcecc0 |
completed | March 8, 2026, 4:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b224f94f3881909a277c45c9add0f5 |
completed | March 12, 2026, 2:29 a.m. |
Created at: March 8, 2026, 3:05 p.m.