Triple

T8650984
Position Surface form Disambiguated ID Type / Status
Subject Marton Csokas E205097 entity
Predicate notableWork P4 FINISHED
Object Evilenko
Evilenko is a 2004 psychological horror-thriller film loosely inspired by the crimes of Soviet serial killer Andrei Chikatilo.
E749699 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: Evilenko | Statement: [Marton Csokas, notableWork, Evilenko]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Evilenko
Context triple: [Marton Csokas, notableWork, Evilenko]
  • A. Max Zorin
    Max Zorin is the main villain in the James Bond film "A View to a Kill," a ruthless industrialist plotting to destroy Silicon Valley for financial gain.
  • B. Grigori
    Grigori is the given name of Grigori Rasputin, the controversial Russian mystic and advisor to the Romanov royal family in the early 20th century.
  • C. Urich
    Urich is a surname most notably associated with American actor Robert Urich, known for his roles in television series such as "Spenser: For Hire" and "Vega$."
  • D. Rykove
    Rykove is a former name of the industrial city now known as Yenakiieve in eastern Ukraine.
  • E. Andross
    Andross is the primary villain of the Star Fox video game series, a mad scientist and powerful ape-like warlord who threatens the Lylat System.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Evilenko
Triple: [Marton Csokas, notableWork, Evilenko]
Generated description
Evilenko is a 2004 psychological horror-thriller film loosely inspired by the crimes of Soviet serial killer Andrei Chikatilo.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Evilenko
Target entity description: Evilenko is a 2004 psychological horror-thriller film loosely inspired by the crimes of Soviet serial killer Andrei Chikatilo.
  • A. Max Zorin
    Max Zorin is the main villain in the James Bond film "A View to a Kill," a ruthless industrialist plotting to destroy Silicon Valley for financial gain.
  • B. Grigori
    Grigori is the given name of Grigori Rasputin, the controversial Russian mystic and advisor to the Romanov royal family in the early 20th century.
  • C. Urich
    Urich is a surname most notably associated with American actor Robert Urich, known for his roles in television series such as "Spenser: For Hire" and "Vega$."
  • D. Rykove
    Rykove is a former name of the industrial city now known as Yenakiieve in eastern Ukraine.
  • E. Andross
    Andross is the primary villain of the Star Fox video game series, a mad scientist and powerful ape-like warlord who threatens the Lylat System.
  • 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_69ca834e56848190abb0eeaec9dedd32 completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc48150e6c8190a7a3b92b4b640858 completed March 31, 2026, 10:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69ceccc95b588190b5e44c73cf93d18b completed April 2, 2026, 8:08 p.m.
NEDg Description generation batch_69cece1681288190a6c99407bc2f0bdd completed April 2, 2026, 8:14 p.m.
NED2 Entity disambiguation (via description) batch_69cecec118ac81909fbcafe841354c32 completed April 2, 2026, 8:17 p.m.
Created at: March 30, 2026, 6:29 p.m.