Triple
T23688194
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hubert Davis |
E585223
|
entity |
| Predicate | threePointFieldGoalPercentageLeader |
P91603
|
FINISHED |
| Object | NBA 1993–94 season |
—
|
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: NBA 1993–94 season | Statement: [Hubert Davis, threePointFieldGoalPercentageLeader, NBA 1993–94 season]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: threePointFieldGoalPercentageLeader Context triple: [Hubert Davis, threePointFieldGoalPercentageLeader, NBA 1993–94 season]
-
A.
threePointPercentageLeader
chosen
Indicates that the subject holds the highest three-point field goal percentage within a specified group or competition.
-
B.
NBAFieldGoalPercentageLeader
Indicates that the subject is the player who led the NBA in field goal percentage for a given season or time period.
-
C.
threePointPercentageMinimum
Indicates that an entity’s three-point shooting percentage meets or exceeds a specified minimum threshold.
-
D.
threePointShooter
Indicates that an entity is characterized by the ability to successfully make three-point shots in basketball.
-
E.
MVPThreePointersMade
Indicates the number of three-point field goals successfully made by the MVP in a game or season.
- 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_69e249037ce0819088b149608e98f685 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b5bfe15c8190af2b4c451bccae16 |
completed | April 29, 2026, 7:39 a.m. |
| PD | Predicate disambiguation | batch_69f155d5265881908e43a9696b6a6d0f |
completed | April 29, 2026, 12:50 a.m. |
Created at: April 17, 2026, 6:52 p.m.