Triple
T7074582
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | KwaZulu homeland |
E164783
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Ulundi |
E161017
|
NE 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: Ulundi | Statement: [KwaZulu homeland, capital, Ulundi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ulundi Context triple: [KwaZulu homeland, capital, Ulundi]
-
A.
Ulundi
chosen
Ulundi is a historic town in KwaZulu-Natal, South Africa, best known as the former royal and political center of the Zulu Kingdom and the site of key events in the Anglo-Zulu War.
-
B.
Lobamba
Lobamba is the traditional and legislative capital of Eswatini, serving as the seat of the Swazi monarchy and key national institutions.
-
C.
Gqeberha
Gqeberha is a major coastal city in South Africa’s Eastern Cape, known as an important industrial, commercial, and port hub.
-
D.
Egoli
Egoli is a common nickname for Johannesburg, South Africa’s major economic hub often referred to as the "City of Gold."
-
E.
Manzini
Manzini is a major city in Eswatini that serves as an important commercial and transport hub of the country.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69c6887cbc6c8190bdfac42d940f4d8a |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e4ccb42c81909f5627aa97db7a84 |
completed | March 27, 2026, 8:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7a31a43b481908e535afc393b242a |
completed | March 28, 2026, 9:44 a.m. |
Created at: March 27, 2026, 2:39 p.m.