Triple
T16426123
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sobhuza II |
E398946
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Ndlovukati Ntombi Tfwala |
E398947
|
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: Ndlovukati Ntombi Tfwala | Statement: [Sobhuza II, spouse, Ndlovukati Ntombi Tfwala]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ndlovukati Ntombi Tfwala Context triple: [Sobhuza II, spouse, Ndlovukati Ntombi Tfwala]
-
A.
Thandekile Ndlovu
Thandekile Ndlovu is a South African royal figure known as one of the wives of the late Zulu King Goodwill Zwelithini kaBhekuzulu.
-
B.
Nokuthula Mhlaba
Nokuthula Mhlaba is known as the wife of South African anti-apartheid activist and politician Raymond Mhlaba.
-
C.
Sithembiso Khumalo
Sithembiso Khumalo is an actor known for appearing in the 2006 political thriller film "Catch a Fire."
-
D.
Ntfombi Tfwala
chosen
Ntfombi Tfwala is a Swazi royal figure who served as Queen Regent of Eswatini and is the mother of King Mswati III.
-
E.
Nompumelelo Ntuli
Nompumelelo Ntuli is a South African woman best known as one of the wives of former South African president Jacob Zuma.
- 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_69d87f2b9024819085c20e52de95d583 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e328faa7448190a2606f1b37ea0a3d |
completed | April 18, 2026, 6:47 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a004f457b8c8190b278697ef43301cb |
completed | May 10, 2026, 9:26 a.m. |
Created at: April 10, 2026, 5:09 a.m.