Triple

T1452572
Position Surface form Disambiguated ID Type / Status
Subject Karelia E31324 entity
Predicate language P15 FINISHED
Object Karelian language E72966 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: Karelian language | Statement: [Karelia, language, Karelian language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Karelian language
Context triple: [Karelia, language, Karelian language]
  • A. Karelian language chosen
    The Karelian language is a Uralic language closely related to Finnish, traditionally spoken by the Karelian people in parts of Finland and northwestern Russia.
  • B. 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.
  • C. Livonian language
    The Livonian language is an almost extinct Uralic language historically spoken by the Livonian people along the northern coast of Latvia.
  • D. Meänkieli
    Meänkieli is a Finnic minority language closely related to Finnish, traditionally spoken by the Tornedalian people in northern Sweden.
  • E. Finnish language
    Finnish is a Uralic language primarily spoken in Finland, known for its complex grammar, extensive case system, and agglutinative structure.
  • 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_69a499171a28819085b993a3ac78e363 completed March 1, 2026, 7:52 p.m.
NER Named-entity recognition batch_69a4c57d34cc8190801b769d9d9b2e2e completed March 1, 2026, 11:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69ad08c6f7c881908d1ef9f7897895a6 completed March 8, 2026, 5:27 a.m.
Created at: March 1, 2026, 8 p.m.