Triple
T35410881
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jamestown |
E1023507
|
entity |
| Predicate | nearUniversityTown |
P68402
|
FINISHED |
| Object | Stellenbosch |
—
|
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: Stellenbosch | Statement: [Jamestown, nearUniversityTown, Stellenbosch]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nearUniversityTown Context triple: [Jamestown, nearUniversityTown, Stellenbosch]
-
A.
adjacentToCampusOf
Indicates that one entity is located next to or directly bordering the campus area of another entity.
-
B.
campusProximity
chosen
Indicates that one entity is located near, adjacent to, or within a short distance of a campus associated with the other entity.
-
C.
suburbanCampus
Indicates that an educational institution’s campus is located in a suburban area, typically outside a central urban core but not in a rural setting.
-
D.
containsUniversityCity
Indicates that a given region or area includes within its boundaries a city that hosts a university.
-
E.
mainCampusNeighborhood
Indicates that a neighborhood is the primary surrounding or associated area of a campus.
- 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_69f76df54bac8190bd0d3b0eb35cda5f |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f795672b40819087ccce744e044124 |
completed | May 3, 2026, 6:35 p.m. |
| PD | Predicate disambiguation | batch_69f7910770108190bdd39ddb5d304f54 |
completed | May 3, 2026, 6:16 p.m. |
Created at: May 3, 2026, 4:03 p.m.