Triple
T14699862
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chud |
E345266
|
entity |
| Predicate | relatedTo |
P37
|
FINISHED |
| Object | Veps |
E657055
|
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: Veps | Statement: [Chud, relatedTo, Veps]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Veps Context triple: [Chud, relatedTo, Veps]
-
A.
Veps language
Veps language is a Finnic Uralic language spoken by the Veps people in northwestern Russia, closely related to Finnish and Karelian.
-
B.
Vepsians
chosen
Vepsians are a small Finno-Ugric ethnic group indigenous to northwestern Russia, known for their distinct Uralic language and traditional rural culture.
-
C.
Karelian–Veps dialect continuum
The Karelian–Veps dialect continuum is a chain of closely related Finnic dialects and languages spoken between the Karelian and Veps language areas in northwestern Russia.
-
D.
Vainakh
Vainakh refers to the closely related Chechen and Ingush peoples of the North Caucasus, sharing a common language group, culture, and historical heritage.
-
E.
Mordva
Mordva is the collective name for the Mordvin people, a Finno-Ugric ethnic group indigenous to the Volga region of Russia with distinct Erzya and Moksha subgroups.
- 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_69d822e4a8c08190a155df736bb7bc13 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb605f5948190ab6b20887c4b6833 |
completed | April 14, 2026, 9:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fde191ef6081908434db8d89ad38cb |
completed | May 8, 2026, 1:13 p.m. |
Created at: April 10, 2026, 1:28 a.m.