Triple

T11172322
Position Surface form Disambiguated ID Type / Status
Subject Viking (film) E264304 entity
Predicate castMember P1668 FINISHED
Object Andrey Smolyakov
Andrey Smolyakov is a Russian film and theater actor known for his extensive work in Soviet and post-Soviet cinema and television.
E1189347 NE FINISHED

How this triple was built (4 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: Andrey Smolyakov | Statement: [Viking (film), castMember, Andrey Smolyakov]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Andrey Smolyakov
Context triple: [Viking (film), castMember, Andrey Smolyakov]
  • A. Sergey Sokolov
    Sergey Sokolov was a Soviet military leader and Marshal of the Soviet Union who served as the USSR’s Minister of Defense during the 1980s.
  • B. Sergei Smirnov
    Sergei Smirnov is a Russian mathematician known for his contributions to probability theory and mathematical physics.
  • C. Andreyan Zakharov
    Andreyan Zakharov was a prominent Russian neoclassical architect of the early 19th century, best known for shaping the monumental imperial style of St. Petersburg.
  • D. Andrei Nikolishin
    Andrei Nikolishin is a former Russian professional ice hockey center who played in the NHL and internationally for the Russian national team.
  • E. Andrei Voronkov
    Andrei Voronkov is a computer scientist known for his influential work in automated reasoning and theorem proving.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Andrey Smolyakov
Triple: [Viking (film), castMember, Andrey Smolyakov]
Generated description
Andrey Smolyakov is a Russian film and theater actor known for his extensive work in Soviet and post-Soviet cinema and television.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Andrey Smolyakov
Target entity description: Andrey Smolyakov is a Russian film and theater actor known for his extensive work in Soviet and post-Soviet cinema and television.
  • A. Sergey Sokolov
    Sergey Sokolov was a Soviet military leader and Marshal of the Soviet Union who served as the USSR’s Minister of Defense during the 1980s.
  • B. Sergei Smirnov
    Sergei Smirnov is a Russian mathematician known for his contributions to probability theory and mathematical physics.
  • C. Andreyan Zakharov
    Andreyan Zakharov was a prominent Russian neoclassical architect of the early 19th century, best known for shaping the monumental imperial style of St. Petersburg.
  • D. Andrei Nikolishin
    Andrei Nikolishin is a former Russian professional ice hockey center who played in the NHL and internationally for the Russian national team.
  • E. Andrei Voronkov
    Andrei Voronkov is a computer scientist known for his influential work in automated reasoning and theorem proving.
  • F. None of above. chosen

Provenance (5 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_69d6aa9dafac8190bd90d2c74f661aa7 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e89660208190b1d9e91529f5d246 completed April 9, 2026, 5:57 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffcf0513f88190b2405ffc32f1e9c7 completed May 10, 2026, 12:19 a.m.
NEDg Description generation batch_69ffd0bfc05881908d7223c52050ea14 completed May 10, 2026, 12:26 a.m.
NED2 Entity disambiguation (via description) batch_69ffd159dbcc81908ac586a6b8de57cf completed May 10, 2026, 12:29 a.m.
Created at: April 8, 2026, 9:29 p.m.