Triple
T10390015
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eyak |
E244865
|
entity |
| Predicate | relatedEthnicGroup |
P1969
|
FINISHED |
| Object | Tlingit |
E9440
|
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: Tlingit | Statement: [Eyak, relatedEthnicGroup, Tlingit]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tlingit Context triple: [Eyak, relatedEthnicGroup, Tlingit]
-
A.
Tlingit
chosen
Tlingit is an Indigenous language of the Pacific Northwest Coast, traditionally spoken by the Tlingit people of southeastern Alaska and western Canada.
-
B.
Athabaskan–Eyak–Tlingit
Athabaskan–Eyak–Tlingit is a proposed Native North American language family grouping that links the Athabaskan languages, Eyak, and Tlingit into a single genetic unit.
-
C.
Alutiiq
Alutiiq is an Indigenous language of the Alutiiq (Sugpiaq) people of south-central coastal Alaska, particularly Kodiak Island and the surrounding regions.
-
D.
Inupiaq
Inupiaq is an Indigenous Inuit language spoken by the Inupiat people of northern and northwestern Alaska and parts of Arctic Canada.
-
E.
Eyak language
The Eyak language is an extinct Na-Dené language once spoken by the Eyak people of south-central Alaska, now primarily documented through linguistic records and revitalization efforts.
- 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_69d381b5116081908d85227bab6d3c0c |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4e9b4f7d08190bcb16d3b4c8f22ad |
completed | April 7, 2026, 11:25 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d87e7adc3881909731d5289f370b8b |
completed | April 10, 2026, 4:37 a.m. |
Created at: April 6, 2026, 12:05 p.m.