Triple
T12171092
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shelden Williams |
E289965
|
entity |
| Predicate | collegeTeamPointsRecord |
P103133
|
FINISHED |
| Object | over 1,700 career points at Duke |
—
|
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: over 1,700 career points at Duke | Statement: [Shelden Williams, collegeTeamPointsRecord, over 1,700 career points at Duke]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: collegeTeamPointsRecord Context triple: [Shelden Williams, collegeTeamPointsRecord, over 1,700 career points at Duke]
-
A.
collegeTeamPointsRecordHolder
Indicates that the subject is the record-holding individual or team for the highest number of points scored for a particular college team.
-
B.
collegeTeamPointsPerGameLeader
Indicates the player who leads a college team in average points scored per game.
-
C.
collegeTeamPoints
Indicates the number of points scored or accumulated by a college sports team in a particular game, season, or competition.
-
D.
collegeTeamAssists
Indicates that one college sports team provides assistance or support to another team.
-
E.
recordTeam
Indicates that a particular team is officially documented or stored as part of a record in a system or dataset.
- 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_69d6ab4d6c00819095a9a7c35de83cfb |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d91621ca6c81908365732f361aef13 |
completed | April 10, 2026, 3:24 p.m. |
| PD | Predicate disambiguation | batch_69d9150e85348190b9b47cda4a17dcd0 |
completed | April 10, 2026, 3:19 p.m. |
| PDg | Predicate description generation | batch_69d916165c708190bf0745e125589f46 |
completed | April 10, 2026, 3:24 p.m. |
Created at: April 8, 2026, 9:50 p.m.