Triple

T1678670
Position Surface form Disambiguated ID Type / Status
Subject Bill Nighy E36288 entity
Predicate characterPortrayed P1507 FINISHED
Object Viktor
Viktor is a powerful and ancient vampire elder from the "Underworld" film series, portrayed by actor Bill Nighy.
 E258120 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: Viktor | Statement: [Bill Nighy, characterPortrayed, Viktor]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Viktor
Context triple: [Bill Nighy, characterPortrayed, Viktor]
  • A. Viktor
    Viktor is the given name of Viktor Frankl, the Austrian neurologist, psychiatrist, and Holocaust survivor who founded logotherapy and wrote "Man’s Search for Meaning."
  • B. Eduard
    Eduard was the younger son of physicist Albert Einstein, known for his promising studies in psychiatry and his lifelong struggle with schizophrenia.
  • C. Eduard
    Eduard is a central character in Paulo Coelho’s novel "Veronika Decides to Die," portrayed as a sensitive, introspective young man whose relationship with the protagonist profoundly influences her view of life and death.
  • D. Vasily
    Vasily is a masculine given name of Slavic origin, commonly used in Russian-speaking countries.
  • E. Ivan
    Ivan is a common Slavic male given name widely used in Russia and other Eastern European countries, equivalent to "John" in English.
  • 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: Viktor
Triple: [Bill Nighy, characterPortrayed, Viktor]
Generated description
Viktor is a powerful and ancient vampire elder from the "Underworld" film series, portrayed by actor Bill Nighy.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Viktor
Target entity description: Viktor is a powerful and ancient vampire elder from the "Underworld" film series, portrayed by actor Bill Nighy.
  • A. Viktor
    Viktor is the given name of Viktor Frankl, the Austrian neurologist, psychiatrist, and Holocaust survivor who founded logotherapy and wrote "Man’s Search for Meaning."
  • B. Eduard
    Eduard was the younger son of physicist Albert Einstein, known for his promising studies in psychiatry and his lifelong struggle with schizophrenia.
  • C. Eduard
    Eduard is a central character in Paulo Coelho’s novel "Veronika Decides to Die," portrayed as a sensitive, introspective young man whose relationship with the protagonist profoundly influences her view of life and death.
  • D. Vasily
    Vasily is a masculine given name of Slavic origin, commonly used in Russian-speaking countries.
  • E. Ivan
    Ivan is a common Slavic male given name widely used in Russia and other Eastern European countries, equivalent to "John" in English.
  • 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_69a886139ed081909af0940aa9313512 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69aa625f7e1081909c3c4fe76625783a completed March 6, 2026, 5:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae95e04dc88190902f2ae5ae856b20 completed March 9, 2026, 9:41 a.m.
NEDg Description generation batch_69ae96b399608190bfa846c433612142 completed March 9, 2026, 9:45 a.m.
NED2 Entity disambiguation (via description) batch_69ae977aac9c8190b5fecd5fea8893fd completed March 9, 2026, 9:48 a.m.
Created at: March 4, 2026, 7:29 p.m.