Triple
T18170870
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dene Zhatıé |
E435019
|
entity |
| Predicate | hasAlternativeName |
P39
|
FINISHED |
| Object | South Slavey |
—
|
NE NERFINISHED |
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: South Slavey | Statement: [Dene Zhatıé, hasAlternativeName, South Slavey]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: South Slavey Context triple: [Dene Zhatıé, hasAlternativeName, South Slavey]
-
A.
South Slavey
chosen
South Slavey is an Athabaskan Indigenous language spoken primarily by the Slavey (Dene) people in Canada’s Northwest Territories.
-
B.
North Slavey
North Slavey is an Athabaskan Indigenous language spoken primarily by the Slavey (Dene) people in Canada’s Northwest Territories.
-
C.
Assiniboine language
The Assiniboine language is an Indigenous Siouan language traditionally spoken by the Assiniboine people of the Northern Plains in North America.
-
D.
Sibe language
Sibe language is a modern Tungusic language spoken primarily by the Sibe people in Xinjiang, China, and is closely related to Manchu.
-
E.
Dakotan languages
The Dakotan languages are a subgroup of the Siouan language family spoken by several Native American peoples of the Great Plains, including dialects such as Dakota, Lakota, and Nakota.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b90b7a188190b3fc7b8d4a6cd20a |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4df56190c8190a3644333f9050a10 |
completed | April 19, 2026, 1:57 p.m. |
Created at: April 10, 2026, 10:30 a.m.