Triple
T3920875
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Garifuna |
E88954
|
entity |
| Predicate | subfamily |
P4180
|
FINISHED |
| Object | Northern Arawakan |
E29016
|
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: Northern Arawakan | Statement: [Garifuna, subfamily, Northern Arawakan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Northern Arawakan Context triple: [Garifuna, subfamily, Northern Arawakan]
-
A.
Arawakan languages
chosen
The Arawakan languages are one of the largest and most widespread Indigenous language families of the Americas, historically spoken across much of South America and the Caribbean.
-
B.
Carib languages
Carib languages are a family of indigenous languages spoken primarily in northern South America and the Caribbean, historically associated with the Carib peoples and influential as a substrate in several regional creoles.
-
C.
Arawak
The Arawak are a group of indigenous peoples of the Americas, historically known for their widespread presence across the Caribbean and parts of South America and for being among the first Native peoples encountered by Europeans.
-
D.
Marquesic languages
Marquesic languages are a subgroup of the Austronesian language family spoken primarily in the Marquesas Islands and surrounding regions of Polynesia.
-
E.
Tucanoan languages
The Tucanoan languages are a family of indigenous languages spoken primarily in the northwestern Amazon Basin of Colombia, Brazil, and Peru, known for complex evidentiality systems and extensive multilingualism among their speakers.
- 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_69aed955229881909e85e73ffab1d343 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeed5c28b08190b32ce81e5bd8f586 |
completed | March 9, 2026, 3:55 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5286c807481908a67471da777b264 |
completed | March 14, 2026, 9:20 a.m. |
Created at: March 9, 2026, 3:22 p.m.