Triple
T21429021
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ice Castles |
E528633
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Robby Benson |
—
|
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: Robby Benson | Statement: [Ice Castles, starring, Robby Benson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Robby Benson Context triple: [Ice Castles, starring, Robby Benson]
-
A.
Robby Benson
chosen
Robby Benson is an American actor, voice actor, and director best known for voicing the Beast in Disney’s animated film "Beauty and the Beast" (1991).
-
B.
Robby Keough
Robby Keough is a fictional military officer and disease-control specialist featured in the medical disaster film "Outbreak."
-
C.
Robby Keene
Robby Keene is a central character in the Cobra Kai series, the estranged son of Johnny Lawrence who becomes a skilled karate fighter caught between rival dojos and father figures.
-
D.
Robby Shaffer
Robby Shaffer is the drummer and a founding member of the contemporary Christian band MercyMe.
-
E.
Roby Marshall
Roby Marshall is the husband of American actress Tracey Gold, known for her role on the sitcom "Growing Pains."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c455f3688190810bc96365791b0f |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ee813db52c8190ac933bc6ec4dbf77 |
completed | April 26, 2026, 9:18 p.m. |
Created at: April 16, 2026, 5:49 p.m.