Triple
T17973358
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peridot |
E449401
|
entity |
| Predicate | voiceActor |
P1507
|
FINISHED |
| Object | Shelby Rabara |
—
|
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: Shelby Rabara | Statement: [Peridot, voiceActor, Shelby Rabara]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Shelby Rabara Context triple: [Peridot, voiceActor, Shelby Rabara]
-
A.
Shelby Rabara
chosen
Shelby Rabara is an American actress and dancer best known for voicing Peridot in the animated series "Steven Universe."
-
B.
Shelby Blackstock
Shelby Blackstock is an American professional race car driver and the son of country music star Reba McEntire.
-
C.
Shelby Roos
Shelby Roos is an American political consultant and strategist best known for her work in Democratic politics and her past marriage to actor and comedian Tom Arnold.
-
D.
Sharrieff Pugh
Sharrieff Pugh is an actor known for his role in the film "In the Cut."
-
E.
Shea Daniels
Shea Daniels is a former gang leader and criminal informant who becomes part of a special team of convicts helping U.S. Marshals track down escaped prisoners in the TV series "Breakout Kings."
- 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_69d8b9f9927c8190a006110c8b996e61 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4b1fca04481908f0dd875953fd82f |
completed | April 19, 2026, 10:44 a.m. |
Created at: April 10, 2026, 10:22 a.m.