Triple
T13623432
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Donnie Shell |
E325515
|
entity |
| Predicate | fumbleRecoveriesInNFL |
P41414
|
FINISHED |
| Object | 19 |
—
|
LITERAL FINISHED |
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: 19 | Statement: [Donnie Shell, fumbleRecoveriesInNFL, 19]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fumbleRecoveriesInNFL Context triple: [Donnie Shell, fumbleRecoveriesInNFL, 19]
-
A.
careerFumbleRecoveries
chosen
Indicates the total number of times an entity has recovered a fumble over the course of their entire career.
-
B.
fumbleReturnTouchdowns
Indicates the number of touchdowns a player or team scores by recovering an opponent’s fumble and returning it to the end zone.
-
C.
careerForcedFumbles
Indicates the total number of times a player has caused an opponent to lose possession of the ball via a fumble over the course of their entire career.
-
D.
decidingPlayFumbleRecoveredBy
Indicates that a particular play is determined or ruled based on which player or team recovered a fumbled ball.
-
E.
sportNumberOfReceptionsNFL
Indicates the number of receptions a player has made in NFL games.
- 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_69d8076aae28819092cf636190ee5529 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbc60635d08190899806fe8936f02a |
completed | April 12, 2026, 4:19 p.m. |
| PD | Predicate disambiguation | batch_69dbbe85e1c4819095194f4b7f9f6118 |
completed | April 12, 2026, 3:47 p.m. |
Created at: April 9, 2026, 9:50 p.m.