Triple
T3111863
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Manicaland Province |
E64969
|
entity |
| Predicate | hasTown |
P847
|
FINISHED |
| Object | Nyanga |
E64970
|
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: Nyanga | Statement: [Manicaland Province, hasTown, Nyanga]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nyanga Context triple: [Manicaland Province, hasTown, Nyanga]
-
A.
Nanyuki
Nanyuki is a Kenyan town on the equator that serves as a popular gateway to Mount Kenya and the surrounding highland wilderness.
-
B.
Kisumu
Kisumu is a major Kenyan city on the shores of Lake Victoria, serving as a key commercial and transport hub in western Kenya.
-
C.
Lake Kyoga
Lake Kyoga is a large, shallow freshwater lake in central Uganda that forms part of the Nile River system and supports important fisheries, wetlands, and local transportation.
-
D.
Lusoga
Lusoga is a Bantu language spoken primarily by the Basoga people in eastern Uganda.
-
E.
Nyanga Highlands
chosen
Nyanga Highlands is a mountainous region in eastern Zimbabwe known for its scenic landscapes, cool climate, and popular hiking and holiday resorts.
- 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_69ad857eeaf48190b34ebfdaa7a264cf |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada43b0b3c8190a828c9cfcf730ed9 |
completed | March 8, 2026, 4:30 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b20f5cfc7c8190b867794c0e9a271e |
completed | March 12, 2026, 12:57 a.m. |
Created at: March 8, 2026, 3:04 p.m.