Triple

T456595
Position Surface form Disambiguated ID Type / Status
Subject Kartvelian languages E7246 entity
Predicate hasSubgroup P747 FINISHED
Object Svan language E57216 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: Svan language | Statement: [Kartvelian languages, hasSubgroup, Svan language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Svan language
Context triple: [Kartvelian languages, hasSubgroup, Svan language]
  • A. Svan language chosen
    Svan language is a highly conservative and endangered Kartvelian language spoken by the Svan people in the Svaneti region of northwestern Georgia.
  • B. Elfdalian
    Elfdalian is a highly conservative North Germanic language spoken in the Älvdalen region of Sweden, preserving many archaic features lost in other Scandinavian languages.
  • C. Ladin language
    Ladin language is a Rhaeto-Romance language spoken primarily in the Dolomite mountain region of northern Italy.
  • D. Yugtun
    Yugtun is the Central Alaskan Yup’ik language spoken by Yup’ik people in western and southwestern Alaska.
  • E. Sámi
    The Sámi are an Indigenous Finno-Ugric people of northern Europe, traditionally known for reindeer herding, fishing, and a distinct cultural and linguistic heritage across parts of Norway, Sweden, Finland, and Russia.
  • 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_69a2e7e5c5bc8190a1dc8178218fba40 completed Feb. 28, 2026, 1:04 p.m.
NER Named-entity recognition batch_69a2efa1616481909399f92551a0c9e3 completed Feb. 28, 2026, 1:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69a44f56b3808190b34ddd3e60b84f85 completed March 1, 2026, 2:38 p.m.
Created at: Feb. 28, 2026, 1:12 p.m.