Triple
T22752421
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Blyde River |
E562739
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Graskop |
—
|
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: Graskop | Statement: [Blyde River, near, Graskop]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Graskop Context triple: [Blyde River, near, Graskop]
-
A.
Graskop
chosen
Graskop is a small tourist town in northeastern South Africa known as a gateway to the Panorama Route and nearby natural attractions like waterfalls and the Blyde River Canyon.
-
B.
Wolmaransstad
Wolmaransstad is a small agricultural and mining town in South Africa’s North West province, situated on a major national transport route.
-
C.
Kronstad
Kronstad is a small population centre located within Alta Municipality in northern Norway.
-
D.
Uitenhage
Uitenhage is a South African town in the Eastern Cape known historically for its automotive industry and as part of the greater Port Elizabeth (Gqeberha) urban area.
-
E.
Groblershoop
Groblershoop is a small town in South Africa’s Northern Cape province, known as an agricultural center in the Orange River wine and grape-growing region.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e24551ec7881909a9c924dbea155f6 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f179baa85881909140f41f2428cc98 |
completed | April 29, 2026, 3:23 a.m. |
Created at: April 17, 2026, 3:24 p.m.