Triple

T15946758
Position Surface form Disambiguated ID Type / Status
Subject Arkady Darell E386704 entity
Predicate givenName P17 FINISHED
Object Arkady E739705 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: Arkady | Statement: [Arkady Darell, givenName, Arkady]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Arkady
Context triple: [Arkady Darell, givenName, Arkady]
  • A. Arkady Mordvinov
    Arkady Mordvinov was a prominent Soviet architect known for his influential role in shaping mid-20th-century Moscow’s monumental Stalinist architectural style.
  • B. Konstantin Vershinin
    Konstantin Vershinin was a prominent Soviet military leader who served as a senior commander of the Soviet Air Forces during and after World War II.
  • C. Arkadi chosen
    Arkadi is a masculine given name of Armenian and Slavic origin, commonly used in Eastern Europe and the Caucasus.
  • D. Alyosha Skvortsov
    Alyosha Skvortsov is the young, idealistic Soviet soldier who serves as the central protagonist in the classic 1959 war film "Ballad of a Soldier."
  • E. Aleksei Serebryakov
    Aleksei Serebryakov is a Russian actor known for his intense performances in film and television, including prominent roles in both Russian cinema and international productions.
  • 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_69d86da882448190a82ea962fe343b79 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e156d1a4c08190afc325491ba38870 completed April 16, 2026, 9:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffb5c0c8a481908aa7a40bca15e38e completed May 9, 2026, 10:31 p.m.
Created at: April 10, 2026, 4:53 a.m.