Triple
T22631825
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Walter Sisulu |
E558572
|
entity |
| Predicate | placeOfBirth |
P1
|
FINISHED |
| Object | Engcobo |
—
|
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: Engcobo | Statement: [Walter Sisulu, placeOfBirth, Engcobo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Engcobo Context triple: [Walter Sisulu, placeOfBirth, Engcobo]
-
A.
Ngcobo
chosen
Ngcobo is a small town in South Africa’s Eastern Cape province, known as a rural service and transport hub in the region.
-
B.
Mbekweni
Mbekweni is a predominantly residential township in the Western Cape province of South Africa, situated near Paarl within the Drakenstein municipal area.
-
C.
Ngubengcuka
Ngubengcuka was a 19th-century king of the Thembu people in South Africa and a prominent ancestor of Nelson Mandela.
-
D.
Makhado
Makhado is a major town in South Africa’s Limpopo province, serving as an important commercial and administrative center in the Vhembe region.
-
E.
Mfumukeko
Mfumukeko is the surname of Libérat Mfumukeko, a Burundian diplomat and former Secretary General of the East African Community.
- 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_69e245467d9881908d6985bd0db7a1f1 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f17009ecb0819082f94505b0e2c5b8 |
completed | April 29, 2026, 2:42 a.m. |
Created at: April 17, 2026, 3:02 p.m.