Triple
T13217862
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tshwane |
E314667
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Temba |
E191909
|
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: Temba | Statement: [Tshwane, contains, Temba]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Temba Context triple: [Tshwane, contains, Temba]
-
A.
Temba
chosen
Temba is a township in the City of Tshwane, South Africa, known as a residential area near Hammanskraal in the Gauteng province.
-
B.
Dube
Dube is a residential neighborhood in Soweto, South Africa, known for its historical significance in the anti-apartheid struggle.
-
C.
Lwalu
Lwalu is a Bantu language spoken in parts of Central Africa, classified within Guthrie’s Zone L group of Bantu languages.
-
D.
Simba Makoni
Simba Makoni is a Zimbabwean politician and economist, known for serving as finance minister and later running as an independent candidate in the 2008 presidential election.
-
E.
Mangosuthu
Mangosuthu is the given name of Mangosuthu Buthelezi, a prominent South African Zulu prince and political leader.
- 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_69d806affc688190a25b6ccc588e9c72 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98cf392e08190949ee4d194566395 |
completed | April 10, 2026, 11:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6ff2085f88190be8cfc309d21f9cb |
completed | May 3, 2026, 7:54 a.m. |
Created at: April 9, 2026, 9:18 p.m.