Triple
T176200
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Holy Cross Crusaders baseball team |
E3580
|
entity |
| Predicate | homeInstitutionType |
P303
|
FINISHED |
| Object | private liberal arts college |
—
|
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: private liberal arts college | Statement: [Holy Cross Crusaders baseball team, homeInstitutionType, private liberal arts college]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: homeInstitutionType Context triple: [Holy Cross Crusaders baseball team, homeInstitutionType, private liberal arts college]
-
A.
hostsInstitution
Indicates that one entity serves as the hosting location or organizing body for an institution.
-
B.
typeOfInstitution
chosen
Indicates the specific kind or category of institution that an entity belongs to or is classified as.
-
C.
homeTo
Indicates that a place serves as the primary location, residence, or habitat for a person, group, or thing.
-
D.
workInstitution
Indicates that an entity is employed by or works at a particular institution.
-
E.
campusType
Indicates the classification or category of a campus based on its type (e.g., main, satellite, urban, rural).
- 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_69a25374990081909766d30c79a18e0e |
completed | Feb. 28, 2026, 2:31 a.m. |
| NER | Named-entity recognition | batch_69a258e497788190aeb61d981efb4d1d |
completed | Feb. 28, 2026, 2:54 a.m. |
| PD | Predicate disambiguation | batch_69a25669d99481908c5e82ba8641205a |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:39 a.m.