Triple
T21271232
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sabie River |
E524260
|
entity |
| Predicate | nearbySettlement |
P350
|
FINISHED |
| Object | Skukuza |
—
|
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: Skukuza | Statement: [Sabie River, nearbySettlement, Skukuza]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Skukuza Context triple: [Sabie River, nearbySettlement, Skukuza]
-
A.
Skukuza
chosen
Skukuza is the largest rest camp and administrative headquarters of South Africa’s Kruger National Park, serving as a major hub for wildlife tourism and park operations.
-
B.
Zonkwa
Zonkwa is a town in southern Kaduna State, Nigeria, serving as an important administrative and commercial center for the surrounding area.
-
C.
Kasulu
Kasulu is a town in western Tanzania that serves as one of the main urban and commercial centers of the Kigoma Region.
-
D.
Ngqumbazi
Ngqumbazi was a Zulu royal woman best known as the mother of King Cetshwayo kaMpande of the Zulu Kingdom.
-
E.
Sabie
Sabie is a small forestry and tourism town in northeastern South Africa, known as a gateway to waterfalls and scenic routes near the Drakensberg escarpment.
- 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_69e0b516293c819089458ea2ec85f85e |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e736534c348190a8d29e8d724dd40a |
completed | April 21, 2026, 8:33 a.m. |
Created at: April 16, 2026, 4:01 p.m.