Triple
T17606805
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Trapeze |
E428853
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Thomas Gomez |
—
|
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: Thomas Gomez | Statement: [Trapeze, starring, Thomas Gomez]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Thomas Gomez Context triple: [Trapeze, starring, Thomas Gomez]
-
A.
Thomas Gomez
chosen
Thomas Gomez was an American character actor known for his prolific work in film, television, and theater during the mid-20th century, often portraying memorable supporting roles.
-
B.
Ron Pardo
Ron Pardo is a Canadian actor and voice actor best known for his multiple character roles in the animated children's franchise PAW Patrol, including its feature film adaptation.
-
C.
Frank Caliendo
Frank Caliendo is an American stand-up comedian and impressionist known for his rapid-fire celebrity impersonations and appearances on television shows such as MADtv and Fox NFL Sunday.
-
D.
Lee R. Mayes
Lee R. Mayes is a film producer best known for his work on the comedy movie "White Chicks."
-
E.
John Ventura
John Ventura was an American attorney, author, and consumer law expert known for writing accessible self-help legal guides for the general public.
- 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_69d889e1c6148190ba76241e74688f8b |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e46c4ccef08190aeaa88670364bd74 |
completed | April 19, 2026, 5:46 a.m. |
Created at: April 10, 2026, 5:51 a.m.