Triple
T37001338
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duke vs. Michigan State (2015 NCAA Final Four) |
E915357
|
entity |
| Predicate | dukeLeadingScorer |
P145763
|
FINISHED |
| Object | Justise Winslow |
—
|
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: Justise Winslow | Statement: [Duke vs. Michigan State (2015 NCAA Final Four), dukeLeadingScorer, Justise Winslow]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dukeLeadingScorer Context triple: [Duke vs. Michigan State (2015 NCAA Final Four), dukeLeadingScorer, Justise Winslow]
-
A.
notableDuke
Indicates that a person holds or held the title of duke and is distinguished or prominent in some notable way.
-
B.
maximumScorePerDunk
Indicates the highest number of points that can be awarded for a single dunk action in the given context.
-
C.
mostPointsPerGamePlayer
chosen
Indicates the player who has the highest average number of points scored per game within a given context or season.
-
D.
DukeHomeArena
Indicates that a specified sports team or program uses a particular arena as its home venue at Duke University.
-
E.
NCAATournamentMostOutstandingPlayer
Indicates that the subject was selected as the Most Outstanding Player of the NCAA Tournament in the relevant season or event.
- 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_69f76e8f1a8c81909db172ed31304971 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb154c0fe08190a2e41e7a29b6055f |
completed | May 6, 2026, 10:17 a.m. |
| PD | Predicate disambiguation | batch_69f9fecc005c8190be082a8689193745 |
completed | May 5, 2026, 2:29 p.m. |
Created at: May 3, 2026, 4:14 p.m.