Triple
T26821143
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1997 NBA All-Star Game |
E675248
|
entity |
| Predicate | MVPQuarterPointsRecord |
P161508
|
FINISHED |
| Object | 20 points in a quarter |
—
|
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: 20 points in a quarter | Statement: [1997 NBA All-Star Game, MVPQuarterPointsRecord, 20 points in a quarter]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: MVPQuarterPointsRecord Context triple: [1997 NBA All-Star Game, MVPQuarterPointsRecord, 20 points in a quarter]
-
A.
MVPrecord
Indicates that an entity holds the record for having won the Most Valuable Player (MVP) award the greatest number of times (or in a notable record-setting manner).
-
B.
MVPPoints
Indicates the number of points an entity has earned toward a Most Valuable Player (MVP) recognition or award.
-
C.
MVPGoals
Indicates that an entity has been recognized as the Most Valuable Player (MVP) based on achieving specific performance goals or criteria.
-
D.
MVPFieldGoalsMade
Indicates the number of field goals successfully made by the MVP in a game or season.
-
E.
MVPThreePointersMade
Indicates the number of three-point field goals successfully made by the MVP in a game or season.
- 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_69eee9b6b28481909332f83eb17e5170 |
completed | April 27, 2026, 4:44 a.m. |
| NER | Named-entity recognition | batch_69f61a89d73c8190b1287cab1ce69805 |
completed | May 2, 2026, 3:38 p.m. |
| PD | Predicate disambiguation | batch_69f611ad2eb48190ac1ed0090f13f7a9 |
completed | May 2, 2026, 3:01 p.m. |
| PDg | Predicate description generation | batch_69f6142a0b988190b404d078f73c3cb9 |
completed | May 2, 2026, 3:11 p.m. |
Created at: April 27, 2026, 4:55 a.m.