Triple

T12877440
Position Surface form Disambiguated ID Type / Status
Subject Red Heat E308003 entity
Predicate mainCharacter P1183 FINISHED
Object Ivan Danko
Ivan Danko is a tough, stoic Soviet police captain portrayed by Arnold Schwarzenegger in the 1988 action film "Red Heat."
E1013715 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: Ivan Danko | Statement: [Red Heat, mainCharacter, Ivan Danko]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ivan Danko
Context triple: [Red Heat, mainCharacter, Ivan Danko]
  • A. Vladimir Smicer
    Vladimir Šmicer is a retired Czech attacking midfielder best known for scoring in Liverpool’s dramatic comeback victory over AC Milan in the 2005 UEFA Champions League Final, known as the “Miracle of Istanbul.”
  • B. Ive Svorcina
    Ive Svorcina is a comic book colorist known for his work on major Marvel titles, including the 2015 Secret Wars event series.
  • C. Roman Podhora
    Roman Podhora is a Canadian actor known for his work in film and television, including roles in genre and action projects.
  • D. Alexander Dvornikov
    Alexander Dvornikov is a Russian Army general known for his senior command roles in Russia’s military operations in Syria and Ukraine.
  • E. George Kralovansky
    George Kralovansky is a television producer best known for his executive production work on the live law-enforcement reality series "Live PD."
  • 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: Ivan Danko
Triple: [Red Heat, mainCharacter, Ivan Danko]
Generated description
Ivan Danko is a tough, stoic Soviet police captain portrayed by Arnold Schwarzenegger in the 1988 action film "Red Heat."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ivan Danko
Target entity description: Ivan Danko is a tough, stoic Soviet police captain portrayed by Arnold Schwarzenegger in the 1988 action film "Red Heat."
  • A. Vladimir Smicer
    Vladimir Šmicer is a retired Czech attacking midfielder best known for scoring in Liverpool’s dramatic comeback victory over AC Milan in the 2005 UEFA Champions League Final, known as the “Miracle of Istanbul.”
  • B. Ive Svorcina
    Ive Svorcina is a comic book colorist known for his work on major Marvel titles, including the 2015 Secret Wars event series.
  • C. Roman Podhora
    Roman Podhora is a Canadian actor known for his work in film and television, including roles in genre and action projects.
  • D. Alexander Dvornikov
    Alexander Dvornikov is a Russian Army general known for his senior command roles in Russia’s military operations in Syria and Ukraine.
  • E. George Kralovansky
    George Kralovansky is a television producer best known for his executive production work on the live law-enforcement reality series "Live PD."
  • 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_69d7bdf69bc48190af6c2621f28ca351 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d970fa8474819086a8af3c90f3ca84 completed April 10, 2026, 9:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6b8ccee708190bb4caa604386e3a3 completed May 3, 2026, 2:54 a.m.
NEDg Description generation batch_69f6bafee83c819096469034ca32ff7d completed May 3, 2026, 3:03 a.m.
NED2 Entity disambiguation (via description) batch_69f6bb7a0ae08190813411fa677430aa completed May 3, 2026, 3:05 a.m.
Created at: April 9, 2026, 5:38 p.m.