Triple
T1223946
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tongan language group |
E26284
|
entity |
| Predicate | instanceOf |
P0
|
FINISHED |
| Object | subgroup of Polynesian languages |
C4276
|
CONCEPT FINISHED |
How this triple was built (1 step)
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.
CD
Concept disambiguation
gpt-5-mini-2025-08-07
Target class: subgroup of Polynesian languages Context triple: [Tongan language group, instanceOf, subgroup of Polynesian languages]
-
A.
Malayo-Polynesian language
A Malayo-Polynesian language is a member of a large branch of the Austronesian language family spoken across Southeast Asia, Madagascar, and the Pacific islands, characterized by shared phonological, grammatical, and lexical features.
-
B.
Austronesian language
An Austronesian language is any member of a large family of languages spoken from Madagascar across Island Southeast Asia and the Pacific to Easter Island, characterized by shared phonological, grammatical, and lexical features tracing back to a common ancestral tongue.
-
C.
Austroasiatic language
An Austroasiatic language is a member of a large language family native to Southeast Asia and parts of South Asia, including languages such as Vietnamese, Khmer, and Mon.
-
D.
language family subgroup
chosen
A language family subgroup is a set of closely related languages within a larger language family that share a more recent common ancestor and distinctive linguistic features.
-
E.
Dravidian language
A Dravidian language is a member of a family of primarily South Indian and Sri Lankan languages, such as Tamil, Telugu, Kannada, and Malayalam, that share common historical origins and structural features distinct from Indo-European languages.
- F. None of above.
Provenance (1 batch)
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_69a49484688c8190a1bf285eb396a8b6 |
completed | March 1, 2026, 7:33 p.m. |
Created at: March 1, 2026, 7:47 p.m.