Triple
T28031659
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Miami Sharks |
E708285
|
entity |
| Predicate | quarterbackInFilm |
P164015
|
FINISHED |
| Object | Willie Beamen |
—
|
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: Willie Beamen | Statement: [Miami Sharks, quarterbackInFilm, Willie Beamen]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: quarterbackInFilm Context triple: [Miami Sharks, quarterbackInFilm, Willie Beamen]
-
A.
quarterbackInFilm
chosen
Indicates that a person serves as the quarterback character or plays the quarterback role within a particular film.
-
B.
featuredQuarterback
Indicates that an entity serves as the primary or highlighted quarterback in a particular context, such as a game, season, or team promotion.
-
C.
quarterback
Indicates that an entity performs the role or action of playing as the quarterback in a football context for another entity (such as a team).
-
D.
GreatestShowOnTurfQuarterback
Indicates that the subject is a quarterback who played for the St. Louis Rams during their high-powered offensive era commonly known as "The Greatest Show on Turf."
-
E.
playedWithQuarterback
Indicates that one player participated on the same team at the same time as a specific quarterback, sharing game or practice play together.
- 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_69ef9b6bdd9c8190bb3a574a03774ad1 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f643ed0b7481908cf25f3afec0a61d |
completed | May 2, 2026, 6:35 p.m. |
| PD | Predicate disambiguation | batch_69f641def1e88190a05bf865ced78b23 |
completed | May 2, 2026, 6:26 p.m. |
Created at: April 27, 2026, 8:17 p.m.