Triple
T28031660
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Miami Sharks |
E708285
|
entity |
| Predicate | runningBackInFilm |
P163645
|
FINISHED |
| Object | Julian Washington |
—
|
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: Julian Washington | Statement: [Miami Sharks, runningBackInFilm, Julian Washington]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: runningBackInFilm Context triple: [Miami Sharks, runningBackInFilm, Julian Washington]
-
A.
runningBack
Indicates that one entity is acting as a running back in relation to another entity, typically within the context of an American football play or team.
-
B.
runningBacksCoach
Indicates that one entity serves as the running backs coach (position coach responsible for running backs) for another entity, typically a sports team.
-
C.
runningBackGiants
Indicates that the subject is a running back who plays for the New York Giants football team.
-
D.
passRusher
Indicates that an entity performs the role or action of rushing the passer, typically attempting to pressure or sack the quarterback.
-
E.
runningBackAward
Indicates that an entity has received an award specifically recognizing performance or achievement in the role of running back.
- F. None of above. chosen
Provenance (4 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_69f63c733844819085a729181009c2b6 |
completed | May 2, 2026, 6:03 p.m. |
| PD | Predicate disambiguation | batch_69f63710d17c819084cfe96e6df334fd |
completed | May 2, 2026, 5:40 p.m. |
| PDg | Predicate description generation | batch_69f63893cc188190883ac9321a95d2dc |
completed | May 2, 2026, 5:46 p.m. |
Created at: April 27, 2026, 8:17 p.m.