Triple
T19104013
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Greater Durban area |
E467605
|
entity |
| Predicate | includesTownship |
P22464
|
FINISHED |
| Object | Inanda |
—
|
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: Inanda | Statement: [Greater Durban area, includesTownship, Inanda]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Inanda Context triple: [Greater Durban area, includesTownship, Inanda]
-
A.
Inanda
chosen
Inanda is a township in the eThekwini Metropolitan Municipality near Durban, South Africa, historically significant as the home of several key anti-apartheid figures and movements.
-
B.
Inanda
Inanda is an affluent residential suburb within Sandton, Johannesburg, known for its leafy streets, upscale homes, and proximity to major business and shopping districts.
-
C.
Ngandi
Ngandi is an Aboriginal Australian language traditionally spoken by the Ngandi people of Arnhem Land in the Northern Territory.
-
D.
Bantumi
Bantumi is a digital version of the traditional Mancala-style board game that was popularized on early Nokia mobile phones.
-
E.
Isanzu
Isanzu is a Bantu language spoken by the Isanzu people of north-central Tanzania.
- 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_69d8dd05ac4c8190b1967d8f97f3fb2f |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e36f84048190a62c52411eb55411 |
completed | April 20, 2026, 8:27 a.m. |
Created at: April 10, 2026, 12:04 p.m.