Triple
T23368475
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oroko |
E593391
|
entity |
| Predicate | relatedGroup |
P37
|
FINISHED |
| Object | Bakweri |
—
|
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: Bakweri | Statement: [Oroko, relatedGroup, Bakweri]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bakweri Context triple: [Oroko, relatedGroup, Bakweri]
-
A.
Bakweri
chosen
The Bakweri are an indigenous Bantu-speaking ethnic group of Cameroon, primarily inhabiting the slopes of Mount Cameroon in the country's Southwest Region.
-
B.
Bekwarra
Bekwarra is a notable town and local government area in southeastern Nigeria, recognized for its predominantly agrarian community and cultural heritage within Cross River State.
-
C.
Bargara
Bargara is a coastal town in Queensland, Australia, known for its beaches, proximity to the Great Barrier Reef, and role as a gateway to nearby turtle nesting sites at Mon Repos.
-
D.
Bakairi
Bakairi is an indigenous Cariban language spoken by the Bakairi people of central Brazil.
-
E.
Bakwa
Bakwa is a town and district center in Afghanistan known for its location in the southwestern Farah Province.
- 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_69e25d2593c88190bcdf4a716a94ccb2 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1a0aed374819097d38f51894bee44 |
completed | April 29, 2026, 6:09 a.m. |
Created at: April 17, 2026, 5:32 p.m.