Triple
T36917067
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Texas Tech vs Michigan State |
E913071
|
entity |
| Predicate | mostOutstandingPlayerOfGame |
P25121
|
FINISHED |
| Object | Jarrett Culver |
—
|
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: Jarrett Culver | Statement: [Texas Tech vs Michigan State, mostOutstandingPlayerOfGame, Jarrett Culver]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mostOutstandingPlayerOfGame Context triple: [Texas Tech vs Michigan State, mostOutstandingPlayerOfGame, Jarrett Culver]
-
A.
mostOutstandingPlayerOfChampionshipGame
Indicates that an entity is recognized as the most outstanding player in a specific championship game.
-
B.
mostValuablePlayerAward
Indicates that an entity has received a "Most Valuable Player" award recognizing it as the most outstanding performer in a particular context or competition.
-
C.
worldChampionshipMVP
Indicates that an entity was selected as the Most Valuable Player (MVP) of a world championship event.
-
D.
playerOfTheMatch
chosen
Indicates that the subject was recognized as the standout performer (best player) in a particular match.
-
E.
mostImprovedPlayer
Indicates that an entity has shown the greatest positive improvement in performance or ability over a defined period compared to its peers.
- 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_69f76e885b848190bad82c87e9525486 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb55ad44bc8190a802bdaab36adc94 |
completed | May 6, 2026, 2:52 p.m. |
| PD | Predicate disambiguation | batch_69f7cf79ddb08190a083405cccc14137 |
completed | May 3, 2026, 10:43 p.m. |
Created at: May 3, 2026, 4:13 p.m.