Triple
T18613356
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Northern Region of Nigeria |
E454954
|
entity |
| Predicate | containsCity |
P294
|
FINISHED |
| Object | Lokoja |
—
|
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: Lokoja | Statement: [Northern Region of Nigeria, containsCity, Lokoja]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lokoja Context triple: [Northern Region of Nigeria, containsCity, Lokoja]
-
A.
Lokoja
chosen
Lokoja is a city in central Nigeria located at the strategic confluence of the Niger and Benue rivers and serves as the capital of Kogi State.
-
B.
Banjima
Banjima is an Aboriginal Australian people traditionally associated with the Pilbara region of Western Australia, known for their distinct language and cultural heritage.
-
C.
Tagakaolo
Tagakaolo is an indigenous ethnolinguistic group in the southern Philippines, primarily in parts of Davao and Sarangani, known for its distinct Austronesian language and cultural traditions.
-
D.
Jirapa
Jirapa is a town in Ghana that serves as a local administrative and commercial center in the country’s Upper West Region.
-
E.
Lugau
Lugau is a town in Saxony, Germany, historically shaped by coal mining in the Ore Mountains region.
- 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_69d8d38bbe7c8190bdec3138e7d413c9 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e54d030d488190a992d10d3d28b4ad |
completed | April 19, 2026, 9:45 p.m. |
Created at: April 10, 2026, 11:45 a.m.