Triple
T6776766
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paresí–Xingu subgroup |
E155576
|
entity |
| Predicate | hasReferenceGrammarFor |
P18535
|
FINISHED |
| Object | Waurá language |
E618293
|
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: Waurá language | Statement: [Paresí–Xingu subgroup, hasReferenceGrammarFor, Waurá language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Waurá language Context triple: [Paresí–Xingu subgroup, hasReferenceGrammarFor, Waurá language]
-
A.
Waurá language
chosen
The Waurá language is an Arawakan language spoken by the Waurá people of Brazil’s Upper Xingu region in the Amazon.
-
B.
Warao language
The Warao language is an indigenous language isolate spoken by the Warao people of northeastern Venezuela and nearby regions, particularly in the Orinoco Delta.
-
C.
Juruna language
The Juruna language is an indigenous Tupian language spoken by the Juruna (Yudjá) people of the Xingu region in Brazil.
-
D.
Terena language
The Terena language is an Arawakan indigenous language spoken primarily by the Terena people of Brazil’s Mato Grosso do Sul region.
-
E.
Jarawa language
The Jarawa language is an endangered Ongan language spoken by the indigenous Jarawa people of the Andaman Islands in India.
- 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_69c688162bf8819088b664b5c3b5be7a |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d7c94bac8190ae4b236d1b04bec9 |
completed | March 27, 2026, 7:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c71a803fe08190b4dc32d09e91da07 |
completed | March 28, 2026, 12:02 a.m. |
Created at: March 27, 2026, 2:13 p.m.