Triple
T13705878
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bassa |
E328639
|
entity |
| Predicate | language |
P15
|
FINISHED |
| Object | Bassa language |
E833983
|
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: Bassa language | Statement: [Bassa, language, Bassa language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bassa language Context triple: [Bassa, language, Bassa language]
-
A.
Bassa language
chosen
Bassa language is a Kru language of the Niger-Congo family spoken primarily by the Bassa people in Liberia and neighboring regions.
-
B.
Bajelani language
The Bajelani language is a lesser-known Northwestern Iranian language spoken primarily by Kurdish communities in parts of Iraq and Iran.
-
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.
Bafia language
The Bafia language is a Bantu language spoken primarily by the Bafia people in central Cameroon.
-
E.
Banda-Linda language
The Banda-Linda language is a Banda language spoken by the Banda-Linda people of the Central African Republic.
- 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_69d8076ff62081908a7bd79889edd7a0 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dcad17732c8190bbd0d73107711c99 |
completed | April 13, 2026, 8:45 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7945b63288190819621830ac1c0d6 |
completed | May 3, 2026, 6:30 p.m. |
Created at: April 9, 2026, 9:54 p.m.