Triple
T16333671
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wounaan people |
E396619
|
entity |
| Predicate | language |
P15
|
FINISHED |
| Object | Wounaan language |
E353474
|
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: Wounaan language | Statement: [Wounaan people, language, Wounaan language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wounaan language Context triple: [Wounaan people, language, Wounaan language]
-
A.
Wounaan language
chosen
Wounaan language is an indigenous Chocoan language spoken by the Wounaan people primarily in Panama and Colombia.
-
B.
Wutun language
The Wutun language is a highly mixed Sinitic–Mongolic–Tibetic language spoken by the Wutun people in Qinghai, China, notable for its extensive contact-induced grammatical and lexical fusion.
-
C.
Wauja language
The Wauja language is an indigenous Arawakan language spoken by the Wauja people of Brazil’s Upper Xingu region in the Amazon.
-
D.
Wawonii language
The Wawonii language is an Austronesian language spoken on Wawonii Island in Southeast Sulawesi, Indonesia, and is part of the Bungku–Tolaki language group.
-
E.
Wapishana language
The Wapishana language is an indigenous Arawakan language spoken primarily by the Wapishana people in parts of Brazil and Guyana.
- 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_69d87f255b788190a400eba031dd85d8 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2c4e1da1081909bec6e77e6109dce |
completed | April 17, 2026, 11:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0026173dc081909e00f6647d1f68b3 |
completed | May 10, 2026, 6:30 a.m. |
Created at: April 10, 2026, 5:07 a.m.