Triple
T21814986
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1991 NBA Finals |
E538581
|
entity |
| Predicate | mostPointsPerGame |
P52811
|
FINISHED |
| Object | 31.2 |
—
|
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: 31.2 | Statement: [1991 NBA Finals, mostPointsPerGame, 31.2]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mostPointsPerGame Context triple: [1991 NBA Finals, mostPointsPerGame, 31.2]
-
A.
pointsPerGame
chosen
Indicates the average number of points an entity scores per game over a given set of games.
-
B.
maximumScorePerDunk
Indicates the highest number of points that can be awarded for a single dunk action in the given context.
-
C.
mostGoalsInSingleGamePlayer
Indicates the player who scored the highest number of goals in a single game.
-
D.
mostTriesScoredByPlayer
Indicates that the referenced player holds the record for scoring the highest number of tries, typically within a specified competition, season, or context.
-
E.
MVPGoals
Indicates that an entity has been recognized as the Most Valuable Player (MVP) based on achieving specific performance goals or criteria.
- 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_69e0c473f0f8819086c9d1b4a143bd67 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f07cc99bbc8190bf074930f361af7d |
completed | April 28, 2026, 9:24 a.m. |
| PD | Predicate disambiguation | batch_69e6be815a108190be81d7c987d0c0d6 |
completed | April 21, 2026, 12:02 a.m. |
Created at: April 16, 2026, 6:54 p.m.