Triple
T18366029
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fang communities of Equatorial Guinea |
E440047
|
entity |
| Predicate | subgroup |
P10
|
FINISHED |
| Object | Mvaï |
—
|
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: Mvaï | Statement: [Fang communities of Equatorial Guinea, subgroup, Mvaï]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mvaï Context triple: [Fang communities of Equatorial Guinea, subgroup, Mvaï]
-
A.
Mvaï
chosen
Mvaï is a dialect of the Fang language spoken by Fang communities in Central Africa.
-
B.
Mujuru
Mujuru is a Zimbabwean surname most prominently associated with Joice Mujuru, a veteran politician and former vice president of Zimbabwe.
-
C.
Maasara
Maasara is an industrial and residential district in the Greater Cairo area of Egypt, known for its factories and proximity to the Nile.
-
D.
Mvila
Mvila is an administrative department in Cameroon's South Region, known for its local governance role and regional cultural diversity.
-
E.
Mbalizi
Mbalizi is a town in southwestern Tanzania located within the Mbeya Region, known as a local commercial and transport hub for the surrounding rural areas.
- 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_69d8b918221c8190a9f7b563d64ac677 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e5174e834481909453ba25561d1b1d |
completed | April 19, 2026, 5:56 p.m. |
Created at: April 10, 2026, 10:38 a.m.