Triple
T7455660
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andean languages |
E172115
|
entity |
| Predicate | instanceOf |
P0
|
FINISHED |
| Object | South American languages |
C3517
|
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: South American languages Context triple: [Andean languages, instanceOf, South American languages]
-
A.
Andean language
chosen
An Andean language is any of the indigenous languages historically spoken in the Andean region of South America, such as Quechua and Aymara, characterized by rich agglutinative morphology and deep cultural significance.
-
B.
First Nations of South America
First Nations of South America are the diverse Indigenous peoples and communities of the South American continent, each with distinct cultures, languages, histories, and relationships to their ancestral lands.
-
C.
Oto-Manguean language
An Oto-Manguean language is a member of a large, diverse family of indigenous Mesoamerican languages, primarily spoken in Mexico, characterized by complex tonal systems and significant grammatical and phonological variation.
-
D.
Indigenous language
An Indigenous language is a native tongue traditionally spoken by the original inhabitants of a region, embodying their cultural knowledge, identity, and worldview.
-
E.
Cordilleran language
A Cordilleran language is a member of a proposed subgroup of the Austronesian language family spoken in the Cordillera mountain region of northern Luzon in the Philippines, characterized by shared phonological, lexical, and grammatical features distinct from neighboring language groups.
- 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_69c68a66554c8190add75c65942c0317 |
completed | March 27, 2026, 1:47 p.m. |
Created at: March 27, 2026, 3:15 p.m.