Triple
T12276842
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hausa city-states |
E292609
|
entity |
| Predicate | hasCapital |
P204
|
FINISHED |
| Object | Gwandu |
E963446
|
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: Gwandu | Statement: [Hausa city-states, hasCapital, Gwandu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gwandu Context triple: [Hausa city-states, hasCapital, Gwandu]
-
A.
Gwandu
chosen
Gwandu is a historic town in northwestern Nigeria known as an important center of Islamic scholarship and traditional authority.
-
B.
Ringen
Ringen is a station on the Oslo Metro system that serves as a key endpoint for certain metro lines in Norway’s capital.
-
C.
Banshenchas
Banshenchas is a medieval Irish genealogical tract that records and organizes the pedigrees of notable Irish families and dynasties.
-
D.
Gigante
Gigante is a municipality and town located in the Huila Department of southwestern Colombia, known for its agricultural activities and Andean landscapes.
-
E.
Ganda
Ganda is a Bantu language spoken primarily in Uganda, where it serves as a major lingua franca and the language of the Baganda people.
- 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_69f62a959e7c8190a005f20728cb71e0 |
completed | May 2, 2026, 4:47 p.m. |
Created at: April 8, 2026, 9:52 p.m.