Triple
T15786187
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Northern Kenya |
E382744
|
entity |
| Predicate | hasMajorTown |
P316
|
FINISHED |
| Object | Mandera |
E838534
|
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: Mandera | Statement: [Northern Kenya, hasMajorTown, Mandera]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mandera Context triple: [Northern Kenya, hasMajorTown, Mandera]
-
A.
Mandera
chosen
Mandera is a remote town in northeastern Kenya near the borders with Somalia and Ethiopia, serving as a key regional trading and administrative center.
-
B.
Babati
Babati is a town in northern Tanzania that serves as an administrative and commercial hub near Lake Babati and the Tarangire National Park.
-
C.
Taveta
Taveta is a key border town in southern Kenya near Tanzania, serving as an important regional trade and transport hub.
-
D.
Kajiado
Kajiado is a town in southern Kenya that serves as an administrative and commercial center for the surrounding Maasai-inhabited region.
-
E.
Wazaramo
Wazaramo are a Bantu-speaking ethnic group native to the coastal and near-coastal regions around Dar es Salaam in eastern Tanzania.
- 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_69d86da16e188190b89af699f1ed0bfe |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e0540380448190a025338f0e62e6d1 |
completed | April 16, 2026, 3:14 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff9987140c8190a50da103905a7930 |
completed | May 9, 2026, 8:31 p.m. |
Created at: April 10, 2026, 4:48 a.m.