Triple

T19027443
Position Surface form Disambiguated ID Type / Status
Subject Alexander Burdonsky E465645 entity
Predicate familyName P18 FINISHED
Object Burdonsky NE NERFINISHED

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: Burdonsky | Statement: [Alexander Burdonsky, familyName, Burdonsky]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Burdonsky
Context triple: [Alexander Burdonsky, familyName, Burdonsky]
  • A. Burdonsky chosen
    Burdonsky is a Russian surname most notably borne by theater director Alexander Burdonsky, a grandson of Joseph Stalin.
  • B. Brodinski
    Brodinski is a French DJ and electronic music producer known for his dark, techno-influenced sound and role in shaping the modern French electronic and club scene.
  • C. Buchinsky
    Buchinsky is the original family surname of American actor Charles Bronson, known for his tough-guy roles in action and vigilante films.
  • D. Baklanov
    Baklanov is a Russian surname most notably associated with Soviet politician and aerospace official Oleg Baklanov.
  • E. Dukelsky
    Dukelsky is the original Russian surname of composer and songwriter Vernon Duke, known for classic American standards such as "April in Paris" and "Autumn in New York."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8dd0359648190bc2a9202c5cf29d2 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d73dc404819092059e496662d151 completed April 20, 2026, 7:35 a.m.
Created at: April 10, 2026, 12:02 p.m.