Triple
T23361367
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Extrême-Nord |
E593192
|
entity |
| Predicate | hasEthnicGroup |
P1898
|
FINISHED |
| Object | Mafa |
—
|
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: Mafa | Statement: [Extrême-Nord, hasEthnicGroup, Mafa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mafa Context triple: [Extrême-Nord, hasEthnicGroup, Mafa]
-
A.
Mafa
chosen
The Mafa are an ethnic group of the Mandara Mountains region in northern Cameroon and northeastern Nigeria, known for their terraced agriculture and rich cultural traditions.
-
B.
Maba
Maba are an ethnic group primarily inhabiting eastern Chad and western Sudan, known for their distinct language and cultural traditions.
-
C.
Mangya
Mangya is a remote county-level city in Qinghai Province, China, located in the Qaidam Basin and known for its sparse population and resource-rich desert landscapes.
-
D.
Mada
Mada is an ethnic group in central Nigeria, known for its distinct language and culture and for living in close proximity to the Eggon people.
-
E.
Mado
Mado is a French film written by Gérard Brach, known as one of his notable screenwriting works.
- 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_69e25d24d2a4819092e6ede74c2a918d |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1a0a8669c819098b88ae6712e3f88 |
completed | April 29, 2026, 6:09 a.m. |
Created at: April 17, 2026, 5:30 p.m.