Triple
T26040194
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dover campus |
E647666
|
entity |
| Predicate | isPublicCampusOf |
P9357
|
FINISHED |
| Object | Delaware State University |
—
|
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: Delaware State University | Statement: [Dover campus, isPublicCampusOf, Delaware State University]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isPublicCampusOf Context triple: [Dover campus, isPublicCampusOf, Delaware State University]
-
A.
isCampusFor
Indicates that a location serves as the campus associated with a particular institution or organization.
-
B.
isPublicUniversityCampus
Indicates that a given campus belongs to and is operated as part of a public (state- or government-funded) university.
-
C.
hasPublicUniversityCampus
Indicates that a public university maintains or operates a campus at the specified location.
-
D.
hasCampusOn
Indicates that an institution or organization maintains a campus located on a specified geographic area or site.
-
E.
isPublicInstitutionCampus
chosen
Indicates that a given campus belongs to or is operated by a public (state- or government-run) institution.
- 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_69e77e8c88f08190858c4c81bd2e1b9a |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f60621f3a88190abbe89d50e06422c |
completed | May 2, 2026, 2:11 p.m. |
| PD | Predicate disambiguation | batch_69f5aff889988190ad10bcf1a280f717 |
completed | May 2, 2026, 8:04 a.m. |
Created at: April 22, 2026, 9:08 a.m.