Triple
T13668506
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Boki people |
E327687
|
entity |
| Predicate | language |
P15
|
FINISHED |
| Object | Boki language |
E1005110
|
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: Boki language | Statement: [Boki people, language, Boki language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Boki language Context triple: [Boki people, language, Boki language]
-
A.
Boki language
chosen
The Boki language is a Bendi language spoken by the Boki people of southeastern Nigeria, primarily in Cross River State.
-
B.
Bafia language
The Bafia language is a Bantu language spoken primarily by the Bafia people in central Cameroon.
-
C.
Baniwa language
Baniwa is an Arawakan Indigenous language spoken primarily along the Rio Negro in northwestern Brazil, as well as in parts of Colombia and Venezuela.
-
D.
Baka language
The Baka language is a Central African language spoken primarily by the Baka Pygmy communities in parts of Cameroon, Gabon, and the Republic of the Congo.
-
E.
Batui language
The Batui language is an Austronesian language spoken in Central Sulawesi, Indonesia, and is part of the Saluan–Banggai subgroup.
- 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_69d8076f1fa8819094664a59b55010df |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbc65832688190aea688fee0a7cbdb |
completed | April 12, 2026, 4:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f78b0f56048190bcbc6581a8cdc0f5 |
completed | May 3, 2026, 5:51 p.m. |
Created at: April 9, 2026, 9:52 p.m.