Triple
T1301302
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Uralic languages |
E27768
|
entity |
| Predicate | hasMember |
P10
|
FINISHED |
| Object | Khanty language |
E72594
|
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: Khanty language | Statement: [Uralic languages, hasMember, Khanty language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Khanty language Context triple: [Uralic languages, hasMember, Khanty language]
-
A.
Erzya language
The Erzya language is a Uralic, Finno-Volgaic language spoken primarily by the Erzya Mordvin people in central Russia.
-
B.
Sakha language
The Sakha language is a Turkic language spoken primarily by the Sakha (Yakut) people in northeastern Siberia, where it serves as a major regional and cultural language.
-
C.
Votic language
The Votic language is a nearly extinct Uralic language traditionally spoken by the Votes in Ingria, near the Gulf of Finland in northwestern Russia.
-
D.
Mansi language
chosen
The Mansi language is a Uralic language spoken by the Indigenous Mansi people of western Siberia in Russia, closely related to Khanty and more distantly to Hungarian.
-
E.
Bashkir language
The Bashkir language is a Turkic language spoken primarily by the Bashkir people in Russia, especially in the Republic of Bashkortostan.
- 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_69a496d6682881909ba658f1c1e0e2b0 |
completed | March 1, 2026, 7:43 p.m. |
| NER | Named-entity recognition | batch_69a4c1145c2481908adf22dfd6ce349b |
completed | March 1, 2026, 10:43 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69acd4729af08190a6de5388dab69fee |
completed | March 8, 2026, 1:44 a.m. |
Created at: March 1, 2026, 7:51 p.m.