Triple

T4396758
Position Surface form Disambiguated ID Type / Status
Subject Svan culture E99510 entity
Predicate language P15 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: [Svan culture, language, Svan language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Svan language
Context triple: [Svan culture, language, 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. Kodava language
    Kodava language is a Dravidian language spoken primarily by the Kodava (Coorg) community in the Kodagu district of Karnataka, India.
  • C. Lule Sami language
    Lule Sami language is a Uralic, Sami language spoken primarily in parts of northern Norway and Sweden by the Lule Sámi people.
  • D. Dargwa language
    The Dargwa language is a Northeast Caucasian language spoken primarily by the Dargin people in the Republic of Dagestan, Russia.
  • E. Evenki language
    The Evenki language is a Northern Tungusic language spoken by the Evenki people across Siberia, northeastern China, and Mongolia.
  • 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_69b345506b408190b0e3dee616738a7d completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b352aca86c8190b5af7e6600072066 completed March 12, 2026, 11:56 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5e53ae7bc8190b216319e522b11c6 completed March 14, 2026, 10:46 p.m.
Created at: March 12, 2026, 11:20 p.m.