Triple
T11662010
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ndlela Dlamini |
E277143
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Dlamini |
E271562
|
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: Dlamini | Statement: [Ndlela Dlamini, familyName, Dlamini]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dlamini Context triple: [Ndlela Dlamini, familyName, Dlamini]
-
A.
Dlamini
chosen
Dlamini is a common Southern African surname of Swazi origin, notably associated with the Swazi royal family and various prominent public figures.
-
B.
Thandiwe
Thandiwe is a feminine given name of African origin, notably borne by British-Zimbabwean actress Thandiwe Newton.
-
C.
Mantfombi Dlamini
Mantfombi Dlamini was a Swazi-born princess who became queen consort and later queen regent of the Zulu nation in South Africa.
-
D.
Ramphele
Ramphele is a South African physician, anti-apartheid activist, academic, and businesswoman who became one of the country’s most prominent public intellectuals and political figures.
-
E.
Sibongile Winifred Dlamini
Sibongile Winifred Dlamini is a South African royal figure best known as one of the principal wives of the late Zulu King Goodwill Zwelithini kaBhekuzulu.
- 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_69d6aafbb3c081908a9cdb4ecb8d981d |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a3d29fdc8190af46b6e2badb1df5 |
completed | April 10, 2026, 7:16 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f4171833948190adafe71ab0d9d2de |
completed | May 1, 2026, 2:59 a.m. |
Created at: April 8, 2026, 9:39 p.m.