Triple

T12557948
Position Surface form Disambiguated ID Type / Status
Subject Bernard Hopkins E295265 entity
Predicate foughtNotableOpponent P893 FINISHED
Object Sergey Kovalev E295271 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: Sergey Kovalev | Statement: [Bernard Hopkins, foughtNotableOpponent, Sergey Kovalev]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sergey Kovalev
Context triple: [Bernard Hopkins, foughtNotableOpponent, Sergey Kovalev]
  • A. Sergey Kovalev chosen
    Sergey Kovalev is a Russian former professional boxer and multiple-time light heavyweight world champion known for his formidable punching power.
  • B. Sergei Kovalev
    Sergei Kovalev was a prominent Russian human rights activist, dissident, and politician known for his opposition to Soviet and later Russian authoritarianism.
  • C. Artur Beterbiev
    Artur Beterbiev is a Russian-Canadian professional boxer known for his exceptional knockout power and status as a unified world light heavyweight champion.
  • D. Gavriil Golovkin
    Gavriil Golovkin was a prominent early 18th-century Russian statesman and diplomat who became one of Peter the Great’s closest political allies and a key architect of the empire’s foreign policy.
  • E. Vlad Kliatchko
    Vlad Kliatchko is a senior technology and product executive known for leading core engineering and platform initiatives at Bloomberg L.P.
  • 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_69d6ad9cac2c81908e8a7bed82d1e21d completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d95491d9688190a6b88a939124233e completed April 10, 2026, 7:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69f655895c9c819082f41e79906567c6 completed May 2, 2026, 7:50 p.m.
Created at: April 8, 2026, 11:48 p.m.