Triple
T18476902
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | University of Durban-Westville |
E451456
|
entity |
| Predicate | hadCampusType |
P110
|
FINISHED |
| Object | urban campus |
—
|
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: urban campus | Statement: [University of Durban-Westville, hadCampusType, urban campus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hadCampusType Context triple: [University of Durban-Westville, hadCampusType, urban campus]
-
A.
campusType
chosen
Indicates the classification or category of a campus based on its type (e.g., main, satellite, urban, rural).
-
B.
hostsCampusOf
Indicates that one entity serves as the physical location or site where another entity’s campus is situated or maintained.
-
C.
hasCampusOn
Indicates that an institution or organization maintains a campus located on a specified geographic area or site.
-
D.
hasSurfaceCampus
Indicates that one entity (typically an institution) maintains a physical campus or site located on the surface of another entity (such as a planet or celestial body).
-
E.
hasCollegeCampus
Indicates that an institution or organization possesses or is associated with a specific college campus as a physical or organizational site.
- 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_69d8d38465a0819099b9b42d2a662ac1 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e53063c0108190be71247567b5241b |
completed | April 19, 2026, 7:43 p.m. |
| PD | Predicate disambiguation | batch_69e469d671088190b619de96ea6f92ab |
completed | April 19, 2026, 5:36 a.m. |
Created at: April 10, 2026, 11:35 a.m.