Triple
T22906713
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nodwengu area near Eshowe |
E568465
|
entity |
| Predicate | nearbyTown |
P3883
|
FINISHED |
| Object | Eshowe |
—
|
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: Eshowe | Statement: [Nodwengu area near Eshowe, nearbyTown, Eshowe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Eshowe Context triple: [Nodwengu area near Eshowe, nearbyTown, Eshowe]
-
A.
Eshowe
chosen
Eshowe is a historic town in South Africa’s KwaZulu-Natal province, notable as a center of Zulu history and colonial-era conflict.
-
B.
Phalaborwa
Phalaborwa is a mining and tourism town in northeastern South Africa, known as a gateway to Kruger National Park and for its rich copper and phosphate deposits.
-
C.
Nxai Pan
Nxai Pan is a vast salt pan and seasonal wildlife area in northeastern Botswana, renowned for its open grasslands, baobab trees, and large migrations of zebras and other game.
-
D.
Mafikeng
Mafikeng is a town in South Africa historically known as the site of the famous Siege of Mafeking during the Second Boer War.
-
E.
Shindzuani
Shindzuani is a regional variety of the Comorian language spoken primarily on Anjouan Island in the Comoros.
- 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_69e2458cd9e48190943ad2e34485d939 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1801a48948190b5f51f1d02351fc7 |
completed | April 29, 2026, 3:50 a.m. |
Created at: April 17, 2026, 3:41 p.m.