Triple
T20703534
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dane-zaa |
E508840
|
entity |
| Predicate | relatedEthnicGroup |
P1969
|
FINISHED |
| Object | 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: Slavey | Statement: [Dane-zaa, relatedEthnicGroup, Slavey]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Slavey Context triple: [Dane-zaa, relatedEthnicGroup, Slavey]
-
A.
Slavey
chosen
Slavey refers to a group of Athabaskan-speaking Indigenous peoples of the Northwest Territories in Canada, known for their distinct dialects and traditional subarctic lifestyle.
-
B.
Slaveykov
Slaveykov is a Bulgarian surname most prominently associated with the 19th-century writer and public figure Petko Slaveykov and his culturally influential family.
-
C.
Servant
Servant is a psychological horror television series created by Tony Basgallop and produced by M. Night Shyamalan, known for its unsettling, slow-burn storytelling and eerie domestic setting.
-
D.
Thoosa
Thoosa is a minor sea nymph in Greek mythology, known primarily as the mother of the Cyclops Polyphemus by the sea god Poseidon.
-
E.
Tutrakan
Tutrakan is a town on the Danube River in northeastern Bulgaria, historically significant as the site of major World War I fighting.
- 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_69e0b4c2b2a481909e31e9cb8f81ab55 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6c18dbda081908217dcb61cbf7ba4 |
completed | April 21, 2026, 12:15 a.m. |
Created at: April 16, 2026, 12:13 p.m.