Triple
T23916144
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duna–Pogaya languages |
E602086
|
entity |
| Predicate | instanceOf |
P0
|
FINISHED |
| Object | Papuan languages subgroup |
C19241
|
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: Papuan languages subgroup Context triple: [Duna–Pogaya languages, instanceOf, Papuan languages subgroup]
-
A.
Papuan language
chosen
A Papuan language is any of the numerous non-Austronesian, non-Australian indigenous languages spoken primarily on the island of New Guinea and neighboring regions, representing several distinct and often unrelated language families.
-
B.
Penutian languages subgroup
The Penutian languages subgroup is a proposed family of Native American languages, primarily spoken in western North America, that are hypothesized to share a common ancestral origin based on structural and lexical similarities.
-
C.
Papuan Tip languages
Papuan Tip languages are a subgroup of Oceanic languages spoken at the southeastern tip of New Guinea and nearby islands, characterized by shared phonological and grammatical features distinct from other Oceanic branches.
-
D.
Munda languages subgroup
The Munda languages subgroup is a branch of the Austroasiatic language family spoken primarily in eastern and central India, characterized by agglutinative morphology and distinctive phonological and syntactic features.
-
E.
Austronesian subgroup
An Austronesian subgroup is a classification of related languages within the Austronesian language family that share common historical origins and linguistic features.
- 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_69e2953a187081908346a9f36e85fc98 |
completed | April 17, 2026, 8:16 p.m. |
Created at: April 17, 2026, 8:40 p.m.