Triple

T1576345
Position Surface form Disambiguated ID Type / Status
Subject Andrei Markov E33660 entity
Predicate familyName P18 FINISHED
Object Markov E33660 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: Markov | Statement: [Andrei Markov, familyName, Markov]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Markov
Context triple: [Andrei Markov, familyName, Markov]
  • A. Markov processes
    Markov processes are stochastic processes in which the future evolution depends only on the present state and not on the past history.
  • B. Monte Carlo
    Monte Carlo is a famous district of Monaco renowned for its luxury casinos, upscale resorts, and role as a glamorous hub for high-end tourism and events like the Monaco Grand Prix.
  • C. Martz
    Martz is a surname most notably associated with Mike Martz, an American football coach known for his innovative offensive strategies in the NFL.
  • D. Mark-3
    Mark-3 is the third-generation Jaeger class to which the iconic mech Gipsy Danger belongs in the Pacific Rim universe.
  • E. Andrei Markov chosen
    Andrei Markov is a Russian former professional ice hockey defenseman best known for his long and successful NHL career with the Montreal Canadiens.
  • 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_69a885f27a4c8190a4622252cdf54c00 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a908d400c08190b0f5fc32ad500b80 completed March 5, 2026, 4:38 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad402b44688190b02e6d146f009854 completed March 8, 2026, 9:23 a.m.
Created at: March 4, 2026, 7:27 p.m.