Triple
T16958470
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Defaka |
E411364
|
entity |
| Predicate | hasAlternativeName |
P39
|
FINISHED |
| Object | Afakani |
E1232002
|
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: Afakani | Statement: [Defaka, hasAlternativeName, Afakani]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Afakani Context triple: [Defaka, hasAlternativeName, Afakani]
-
A.
Afakani
chosen
Afakani is an alternative name for the Defaka language, a highly endangered Ijoid language spoken by a small community in Nigeria’s Niger Delta region.
-
B.
Afak
Afak is a town in modern-day Iraq located near the site of the ancient Mesopotamian city of Nuffar (Nippur).
-
C.
Ahfir
Ahfir is a town in northeastern Morocco near the Algerian border, known as a local commercial and transit center within the Oriental region.
-
D.
Afa
Afa is a small commune in the Corse-du-Sud department on the French island of Corsica, located inland near the Gulf of Ajaccio.
-
E.
Afizere
Afizere is a Plateau language spoken by the Afizere (Jarawa) people primarily in and around Jos in central Nigeria.
- 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_69d886c9c9d481909afe222093641cae |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d01e420881909be1d93d7d6772fd |
completed | April 18, 2026, 6:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00d468f5048190aa43b212ec7a7306 |
completed | May 10, 2026, 6:54 p.m. |
Created at: April 10, 2026, 5:31 a.m.