Triple
T32791680
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Purple Raiders football |
E838643
|
entity |
| Predicate | allTimeWinsLeader |
P7621
|
FINISHED |
| Object | Larry Kehres |
—
|
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: Larry Kehres | Statement: [Purple Raiders football, allTimeWinsLeader, Larry Kehres]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: allTimeWinsLeader Context triple: [Purple Raiders football, allTimeWinsLeader, Larry Kehres]
-
A.
allTimeWinsRank
Indicates the relative position or standing of an entity based on its total number of wins accumulated over all time.
-
B.
mostOverallWinsRecord
Indicates that the subject holds the record for having the greatest total number of wins compared to all others in the relevant context.
-
C.
mostOverallWinsHolder
chosen
Indicates that the subject is the entity holding the highest total number of wins overall, compared to all other relevant entities.
-
D.
teamNumberOfWinsLeader
Indicates that the subject is the team currently leading in number of wins, or the number of wins associated with that leading team.
-
E.
winsLeader
Indicates that one entity achieves victory or leadership over another in a competitive or comparative context.
- 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_69f3493c7f6881908edf2aa13631d1e0 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6ce6d659881909ddcec1d2966e020 |
completed | May 3, 2026, 4:26 a.m. |
| PD | Predicate disambiguation | batch_69f6cc1667a48190b42684f6ec22dae9 |
completed | May 3, 2026, 4:16 a.m. |
Created at: May 1, 2026, 1:14 a.m.