Triple
T29986165
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brock Marion |
E761739
|
entity |
| Predicate | careerInterceptionReturnYards |
P168325
|
FINISHED |
| Object | 1,023 |
—
|
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: 1,023 | Statement: [Brock Marion, careerInterceptionReturnYards, 1,023]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: careerInterceptionReturnYards Context triple: [Brock Marion, careerInterceptionReturnYards, 1,023]
-
A.
careerPuntReturnYards
Indicates the total number of yards an entity has gained on punt returns over the course of their entire career.
-
B.
interceptionReturnYards
Indicates the number of yards gained by a defensive player while returning an intercepted pass.
-
C.
careerReceivingYards
Indicates the total number of yards a player has gained by receiving the ball over the course of their entire career.
-
D.
interceptionReturnTouchdowns
Indicates the number of times a defensive player returns an intercepted pass into the opponent’s end zone for a touchdown.
-
E.
careerFumbleRecoveries
Indicates the total number of times an entity has recovered a fumble over the course of their entire career.
- 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_69f2246851148190b8e76206db94b105 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69f67915bf008190b87d771e157bd3c8 |
completed | May 2, 2026, 10:22 p.m. |
| PD | Predicate disambiguation | batch_69f66ec9919881908a187bfc7c4df192 |
completed | May 2, 2026, 9:38 p.m. |
| PDg | Predicate description generation | batch_69f67256d064819094be04fc1bbbc635 |
completed | May 2, 2026, 9:53 p.m. |
Created at: April 29, 2026, 6:36 p.m.