Triple
T130139
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harvard Crimson women’s basketball |
E2635
|
entity |
| Predicate | competitionCategory |
P2440
|
FINISHED |
| Object | college sports |
—
|
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: college sports | Statement: [Harvard Crimson women’s basketball, competitionCategory, college sports]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: competitionCategory Context triple: [Harvard Crimson women’s basketball, competitionCategory, college sports]
-
A.
sportCategory
Indicates that one entity is classified as a type or category of sport to which the other entity (typically a specific sport or sporting event) belongs.
-
B.
typeOfCompetition
chosen
Indicates the specific kind or category of competition in which an entity participates or is involved.
-
C.
competition
Indicates a relationship where two or more entities strive against each other to achieve a superior outcome, advantage, or reward.
-
D.
competitionLevel
Indicates the degree or intensity of competitive pressure or rivalry present in a given context or interaction.
-
E.
competitionFormat
Indicates the specific structure or ruleset under which a competition is organized and conducted.
- 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_69a2520c0f3481908b0ed054a2fca8d0 |
completed | Feb. 28, 2026, 2:25 a.m. |
| NER | Named-entity recognition | batch_69a257845c548190bfb49409988d1c57 |
completed | Feb. 28, 2026, 2:48 a.m. |
| PD | Predicate disambiguation | batch_69a2564da96c8190aa8204de25229c15 |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:30 a.m.