Triple
T24487989
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Randolph–Macon Yellow Jackets men's basketball team |
E617562
|
entity |
| Predicate | hasAlumnusCoach |
P130041
|
FINISHED |
| Object | Gregg Marshall |
—
|
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: Gregg Marshall | Statement: [Randolph–Macon Yellow Jackets men's basketball team, hasAlumnusCoach, Gregg Marshall]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAlumnusCoach Context triple: [Randolph–Macon Yellow Jackets men's basketball team, hasAlumnusCoach, Gregg Marshall]
-
A.
hasAlumni
Indicates that an institution or organization is associated with individuals who formerly attended or graduated from it.
-
B.
hasAlumnusLeague
Indicates that an educational institution has at least one alumnus who is or was a member of a specified sports league.
-
C.
hasAlumnusTeam
Indicates a relationship where an educational institution is associated with a sports team composed of its former students (alumni).
-
D.
hasAlumnusWhoBecame
chosen
Indicates that an institution has at least one alumnus who later attained or assumed a specified role, position, or status.
-
E.
hasAlumniWhoWon
Indicates that an institution has alumni who have won a particular award, honor, or competition.
- 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_69e2d7f4e6bc8190aec540ae3b9ed7f2 |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f2a9d912e88190bc39c05a9d7f407e |
completed | April 30, 2026, 1:01 a.m. |
| PD | Predicate disambiguation | batch_69f2a6a4580481908fddc385f5262f95 |
completed | April 30, 2026, 12:47 a.m. |
Created at: April 18, 2026, 2:22 a.m.