Triple
T15407314
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Keffi |
E368492
|
entity |
| Predicate | connectedByRoadTo |
P11435
|
FINISHED |
| Object | Akwanga |
E368493
|
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: Akwanga | Statement: [Keffi, connectedByRoadTo, Akwanga]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Akwanga Context triple: [Keffi, connectedByRoadTo, Akwanga]
-
A.
Akwanga
chosen
Akwanga is a town and administrative center in central Nigeria known for its role as a commercial and educational hub in Nasarawa State.
-
B.
Ewondo
Ewondo is a Bantu language spoken primarily by the Ewondo people in central Cameroon, including in and around the capital city, Yaoundé.
-
C.
Achagua-Achagua
Achagua-Achagua is an indigenous Arawakan language spoken by the Achagua people of Colombia and Venezuela.
-
D.
Wele-Nzas
Wele-Nzas is a province in mainland Equatorial Guinea known for its forests, border location near Gabon and Cameroon, and the city of Mongomo.
-
E.
Akanland
Akanland is the traditional homeland of the Akan people in West Africa, known for its rich cultural heritage, festivals, and historical kingdoms such as Ashanti.
- 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_69d85a16c68c819099c1b547fbc87b32 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03ea36c6881909eaea48e9608897a |
completed | April 16, 2026, 1:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff1a716248819094fd8b205cc2a3f2 |
completed | May 9, 2026, 11:28 a.m. |
Created at: April 10, 2026, 3:20 a.m.