Triple
T2640433
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Matabeleland |
E62851
|
entity |
| Predicate | majorTown |
P316
|
FINISHED |
| Object | Gwanda |
E149377
|
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: Gwanda | Statement: [Matabeleland, majorTown, Gwanda]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gwanda Context triple: [Matabeleland, majorTown, Gwanda]
-
A.
Gwanda
chosen
Gwanda is a small Zimbabwean town that serves as an administrative and commercial hub in the country’s arid south, known historically for cattle ranching and gold mining.
-
B.
Kalangala
Kalangala is a town on Uganda’s Ssese Islands in Lake Victoria, serving as the administrative and commercial center of Kalangala District.
-
C.
Runyankole
Runyankole is a Bantu language spoken primarily by the Banyankole people in southwestern Uganda.
-
D.
Matadi
Matadi is a major port city in western Democratic Republic of the Congo, serving as the country’s principal seaport and a key gateway for trade between the Atlantic Ocean and the interior via the Congo River.
-
E.
Chinhoyi
Chinhoyi is a town in northern Zimbabwe known as an administrative center and for the nearby Chinhoyi Caves.
- 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_69ab4c3f2dcc819082df80f5e032f690 |
completed | March 6, 2026, 9:50 p.m. |
| NER | Named-entity recognition | batch_69abd8fc8ee881908a9f6820d8934a62 |
completed | March 7, 2026, 7:51 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69af90b8469881909e2c1bd1f4798464 |
completed | March 10, 2026, 3:32 a.m. |
Created at: March 6, 2026, 9:53 p.m.