Triple
T26608521
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Florida Gators |
E667846
|
entity |
| Predicate | footballHeismanTrophyWinner |
P20896
|
FINISHED |
| Object | Steve Spurrier |
—
|
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: Steve Spurrier | Statement: [Florida Gators, footballHeismanTrophyWinner, Steve Spurrier]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: footballHeismanTrophyWinner Context triple: [Florida Gators, footballHeismanTrophyWinner, Steve Spurrier]
-
A.
HeismanTrophyWinner
chosen
Indicates that the subject is the recipient of the Heisman Trophy, awarded annually to the most outstanding player in U.S. college football.
-
B.
namedHeismanTrophyFor
Indicates that an entity has had the Heisman Trophy named in honor of or after it.
-
C.
HeismanTrophyConnection
Indicates a relationship where an entity is connected to the Heisman Trophy, such as by winning, being nominated for, or otherwise being formally associated with the award.
-
D.
heismanTrophyFinalist
Indicates that a person was selected as one of the finalists considered for the Heisman Trophy award in a given year.
-
E.
hasHeismanTrophies
Indicates that the subject has won one or more Heisman Trophy awards.
- F. None of above.
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_69ee9cfd20348190bb1255d2603efb7a |
completed | April 26, 2026, 11:17 p.m. |
| NER | Named-entity recognition | batch_69f61576b3f48190bc87dcdf685b4532 |
completed | May 2, 2026, 3:17 p.m. |
| PD | Predicate disambiguation | batch_69f602d7b1b0819095ddd3b5169f8ce2 |
completed | May 2, 2026, 1:57 p.m. |
Created at: April 27, 2026, 2:15 a.m.