Triple
T20885102
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Swing Vote |
E514256
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Kelsey Grammer |
—
|
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: Kelsey Grammer | Statement: [Swing Vote, starring, Kelsey Grammer]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kelsey Grammer Context triple: [Swing Vote, starring, Kelsey Grammer]
-
A.
Kelsey Grammer
chosen
Kelsey Grammer is an American actor best known for his long-running, Emmy-winning portrayal of Dr. Frasier Crane on the sitcoms "Cheers" and "Frasier."
-
B.
David Hyde Pierce
David Hyde Pierce is an American actor best known for his Emmy-winning role as Dr. Niles Crane on the television sitcom "Frasier."
-
C.
William H. Murray
William H. Murray was an American lawyer and politician who served as the ninth governor of Oklahoma and was a prominent figure in the state’s early political history.
-
D.
Tim Metcalfe
Tim Metcalfe is a music producer best known for his work on Robbie Williams’ album "Take the Crown."
-
E.
Tim Metcalfe
Tim Metcalfe is an American screenwriter known for his work on films such as the horror movie "Bones" (2001) and other genre projects.
- 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_69e0b4f733f081908a401c0b7beb0b9f |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c67c9d1c81908031eb77c124f119 |
completed | April 21, 2026, 12:36 a.m. |
Created at: April 16, 2026, 12:46 p.m.