Triple
T15836430
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marsabit County |
E383996
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Marsabit |
E1196185
|
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: Marsabit | Statement: [Marsabit County, capital, Marsabit]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marsabit Context triple: [Marsabit County, capital, Marsabit]
-
A.
Marsabit
chosen
Marsabit is a remote market and administrative town in northern Kenya, known as a gateway to Marsabit National Park and its surrounding arid highlands.
-
B.
Isiolo
Isiolo is a town in central Kenya that serves as a key transport and commercial hub linking the country’s northern regions with the rest of the nation.
-
C.
Kajiado
Kajiado is a town in southern Kenya that serves as an administrative and commercial center for the surrounding Maasai-inhabited region.
-
D.
Wazaramo
Wazaramo are a Bantu-speaking ethnic group native to the coastal and near-coastal regions around Dar es Salaam in eastern Tanzania.
-
E.
Nakuru
Nakuru is a prominent Kenyan city in the Rift Valley region, known for its proximity to Lake Nakuru National Park and its role as an important agricultural and commercial center.
- 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_69d86da34c888190976e06c4019d415a |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e142e1fcd48190bcb884f6c65db847 |
completed | April 16, 2026, 8:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fffee4f84c81908b2c7e216ef159e0 |
completed | May 10, 2026, 3:43 a.m. |
Created at: April 10, 2026, 4:49 a.m.