Triple
T14068225
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kogi State University |
E338532
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Anyigba |
E1054935
|
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: Anyigba | Statement: [Kogi State University, locatedIn, Anyigba]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Anyigba Context triple: [Kogi State University, locatedIn, Anyigba]
-
A.
Anyigba
chosen
Anyigba is a prominent commercial and educational town in Kogi State, Nigeria, known for hosting Prince Abubakar Audu University and serving as a key hub for the surrounding region.
-
B.
Agbeyangi
Agbeyangi is a town in Ilorin East Local Government Area of Kwara State, Nigeria.
-
C.
Anyama
Anyama is a town located within Ogbia Local Government Area in Bayelsa State, southern Nigeria.
-
D.
Ogwumike
Ogwumike is a Nigerian surname most prominently associated with a family of professional basketball players, including WNBA star Nneka Ogwumike.
-
E.
Igalamela-Odolu
Igalamela-Odolu is a local government area in Kogi State, Nigeria, known for its predominantly Igala population and agrarian communities.
- 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_69d81c67ba6c819091935650dfb3b895 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de568d0404819087e0fe37c72162cb |
completed | April 14, 2026, 3 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcb66aeff8819088239226bbe25fd5 |
completed | May 7, 2026, 3:57 p.m. |
Created at: April 9, 2026, 10:21 p.m.