Triple
T12276839
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hausa city-states |
E292609
|
entity |
| Predicate | hasCapital |
P204
|
FINISHED |
| Object | Keffi |
E368492
|
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: Keffi | Statement: [Hausa city-states, hasCapital, Keffi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Keffi Context triple: [Hausa city-states, hasCapital, Keffi]
-
A.
Keffi
chosen
Keffi is a historic town and commercial center in central Nigeria that serves as one of the key urban settlements in Nasarawa State.
-
B.
Abakaliki
Abakaliki is a major city in southeastern Nigeria known as an administrative, commercial, and agricultural hub.
-
C.
Jalingo
Jalingo is the capital and largest city of Taraba State in northeastern Nigeria, serving as an important administrative and commercial center for the region.
-
D.
Mbuji-Mayi
Mbuji-Mayi is a major city in south-central Democratic Republic of the Congo, known as a key center of the country’s diamond mining industry.
-
E.
Makurdi
Makurdi is the capital city of Benue State in central Nigeria, serving as an important administrative and commercial hub in the region.
- 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_69d6ab6856488190b5d31178d5015f8e |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d91cf06cf08190ac8671dd9bbed03d |
completed | April 10, 2026, 3:53 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f61e6d72d081908c8697257df712f1 |
completed | May 2, 2026, 3:55 p.m. |
Created at: April 8, 2026, 9:52 p.m.