Triple
T21175447
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kwale County |
E521798
|
entity |
| Predicate | hasEthnicGroup |
P1898
|
FINISHED |
| Object | Kikuyu |
—
|
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: Kikuyu | Statement: [Kwale County, hasEthnicGroup, Kikuyu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kikuyu Context triple: [Kwale County, hasEthnicGroup, Kikuyu]
-
A.
Kikuyu
chosen
Kikuyu is a major Bantu language spoken primarily by the Kikuyu people of central Kenya.
-
B.
Kikuyu
Kikuyu is a town in Kenya’s Nairobi Metropolitan Region, known as a fast-growing residential and commercial center west of Nairobi.
-
C.
Coolabah
Coolabah is a small rural town in western New South Wales, Australia, known for its remote outback setting and role as a service stop along regional transport routes.
-
D.
Tarraganda
Tarraganda is a small rural locality situated within the Bega Valley region of New South Wales, Australia, known for its agricultural landscape and proximity to the town of Bega.
-
E.
Wangurri
Wangurri is a Yolŋu Aboriginal Australian language variety spoken by the Wangurri people of northeast Arnhem Land in the Northern Territory.
- 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_69e0b50e30748190b186824a206d39b9 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e7271597288190b04baff9ca8d866c |
completed | April 21, 2026, 7:28 a.m. |
Created at: April 16, 2026, 3 p.m.