Triple
T3355271
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paul Silas |
E70588
|
entity |
| Predicate | reboundsPerGameInCollege |
P22437
|
FINISHED |
| Object | 20.6 |
—
|
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: 20.6 | Statement: [Paul Silas, reboundsPerGameInCollege, 20.6]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reboundsPerGameInCollege Context triple: [Paul Silas, reboundsPerGameInCollege, 20.6]
-
A.
scoredPointsPerGameInCollege
Indicates the average number of points an entity (typically an athlete) scored per game during their college career.
-
B.
playedCollegeBasketballFor
Indicates that a person was a member of and competed for a specific college or university’s basketball team.
-
C.
positionPlayedInCollege
Indicates the specific playing position an individual held on a sports team during their college career.
-
D.
careerReboundsPerGame
Indicates the average number of rebounds a player records per game over the course of their entire career.
-
E.
statRebounds
chosen
Indicates the number of rebounds an entity (typically a player or team) records in a game or over a specified period.
- 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_69ad85a4ef7c8190a29e2bbd6fa454e4 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb2419a808190a54fc03eeec6e42d |
completed | March 8, 2026, 5:30 p.m. |
| PD | Predicate disambiguation | batch_69ada42fbe7c8190b9f185b5ab985f17 |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:13 p.m.