Triple
T225424
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harvard Crimson men's ice hockey |
E4303
|
entity |
| Predicate | campusOrganizationType |
P3580
|
FINISHED |
| Object | varsity athletic team |
—
|
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: varsity athletic team | Statement: [Harvard Crimson men's ice hockey, campusOrganizationType, varsity athletic team]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: campusOrganizationType Context triple: [Harvard Crimson men's ice hockey, campusOrganizationType, varsity athletic team]
-
A.
campusType
Indicates the classification or category of a campus based on its type (e.g., main, satellite, urban, rural).
-
B.
typeOfInstitution
Indicates the specific kind or category of institution that an entity belongs to or is classified as.
-
C.
organizationType
chosen
Indicates the specific category or classification of an organization in terms of its nature, structure, or primary function.
-
D.
hostsCampusOf
Indicates that one entity serves as the physical location or site where another entity’s campus is situated or maintained.
-
E.
cityCampus
Indicates that a campus is located within or associated with a particular city.
- 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_69a257363ffc81909757bde7ab3404da |
completed | Feb. 28, 2026, 2:47 a.m. |
| NER | Named-entity recognition | batch_69a25dec53ac8190912f3d79576131fa |
completed | Feb. 28, 2026, 3:15 a.m. |
| PD | Predicate disambiguation | batch_69a25b5739dc8190bad8bfa330ce0499 |
completed | Feb. 28, 2026, 3:04 a.m. |
Created at: Feb. 28, 2026, 2:53 a.m.