Triple
T79210
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harvard Crimson men’s basketball |
E1588
|
entity |
| Predicate | studentAthletes |
P3611
|
FINISHED |
| Object | undergraduate |
—
|
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: undergraduate | Statement: [Harvard Crimson men’s basketball, studentAthletes, undergraduate]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: studentAthletes Context triple: [Harvard Crimson men’s basketball, studentAthletes, undergraduate]
-
A.
hasNumberOfStudentAthletes
Indicates the relationship that specifies how many student athletes are associated with a given entity.
-
B.
athleticDirector
Indicates that one entity serves as the athletic director (the person in charge of overseeing athletic programs) for another entity, such as a school or organization.
-
C.
hasAthletics
Indicates that an entity participates in, is associated with, or offers athletics-related activities or programs.
-
D.
primarySport
Indicates the main sport with which an entity (such as a person, team, or organization) is most closely associated or primarily involved.
-
E.
collegeTeam
Indicates that one entity is a sports team that represents or is affiliated with a particular college or university.
- 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_69a24c60d19c8190a1b6c105ca59ef5b |
completed | Feb. 28, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69a24fd16c248190a6ee4cd96c388772 |
completed | Feb. 28, 2026, 2:15 a.m. |
| PD | Predicate disambiguation | batch_69a24eb126b48190b410b859c1be99aa |
completed | Feb. 28, 2026, 2:10 a.m. |
| PDg | Predicate description generation | batch_69a24fcfff7c8190adbacd1539829850 |
completed | Feb. 28, 2026, 2:15 a.m. |
Created at: Feb. 28, 2026, 2:06 a.m.