Triple
T7792437
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Banda people |
E180212
|
entity |
| Predicate | language |
P15
|
FINISHED |
| Object | Banda-Banda |
E672477
|
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: Banda-Banda | Statement: [Banda people, language, Banda-Banda]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Banda-Banda Context triple: [Banda people, language, Banda-Banda]
-
A.
Banda-Banda
chosen
Banda-Banda is a dialect of the Central Banda language spoken by Banda communities in the Central African region.
-
B.
Banda Besar
Banda Besar is one of the main volcanic islands in Indonesia’s Banda Sea, known historically as part of the nutmeg-producing Banda Islands.
-
C.
Kabu Kabu
Kabu Kabu is a speculative fiction short story collection by Nnedi Okorafor that blends African folklore, magical realism, and contemporary themes.
-
D.
Tringgus-Sembaan Bidayuh
Tringgus-Sembaan Bidayuh is an Austronesian language spoken by the Bidayuh people in parts of Sarawak, Malaysian Borneo.
-
E.
Bhinneka
Bhinneka is an Indonesian e-commerce company best known as one of the country’s earliest and largest online retailers for electronics and IT products.
- 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_69ca827d22208190b4dc5aa680edcf5d |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cae938714c8190b89917e6ded004da |
completed | March 30, 2026, 9:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cb13cdb4288190ae3cfe1ee4e3e496 |
completed | March 31, 2026, 12:22 a.m. |
Created at: March 30, 2026, 4:30 p.m.