Triple

T15794888
Position Surface form Disambiguated ID Type / Status
Subject Luka Razikashvili E382951 entity
Predicate notableWork P4 FINISHED
Object Bakhtrioni E382955 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: Bakhtrioni | Statement: [Luka Razikashvili, notableWork, Bakhtrioni]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bakhtrioni
Context triple: [Luka Razikashvili, notableWork, Bakhtrioni]
  • A. Bakhtrioni chosen
    Bakhtrioni is a celebrated narrative poem by Georgian writer Vazha-Pshavela, known for its patriotic themes and vivid depiction of highland life and resistance.
  • B. Torgos
    Torgos is a genus of large Old World vultures best known for including the lappet-faced vulture.
  • C. Ratmir
    Ratmir is a Tatar prince who appears as a gallant yet ultimately reformed seducer in Alexander Pushkin’s narrative poem "Ruslan and Ludmila."
  • D. Asparuh
    Asparuh was a 7th-century Bulgar ruler who founded the First Bulgarian Empire in the Balkans and is regarded as one of Bulgaria’s key founding figures.
  • E. Retvizan
    Retvizan was a pre-dreadnought battleship of the Imperial Russian Navy, built in the United States and best known for its service and damage during the Russo-Japanese War, particularly at the Battle of Port Arthur.
  • 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_69d86da16e188190b89af699f1ed0bfe completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e0b4dc887081909d682ae153f06d97 completed April 16, 2026, 10:07 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff90ab23048190a6d976c9a3143647 completed May 9, 2026, 7:53 p.m.
Created at: April 10, 2026, 4:48 a.m.