Triple

T4506302
Position Surface form Disambiguated ID Type / Status
Subject Superman E101338 entity
Predicate enemy P4567 FINISHED
Object Brainiac
Brainiac is a highly intelligent and malevolent alien android in DC Comics, known for shrinking and collecting cities and serving as one of Superman’s most formidable foes.
E447838 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: Brainiac | Statement: [Superman, enemy, Brainiac]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Brainiac
Context triple: [Superman, enemy, Brainiac]
  • A. John Battsek
    John Battsek is a British film producer renowned for his work on acclaimed feature documentaries and sports-related non-fiction films.
  • B. Johnny Wadd
    Johnny Wadd is the fictional hardboiled detective character famously portrayed by adult film actor John Holmes in a series of 1970s pornographic films.
  • C. Scarecrow
    Scarecrow is a Batman supervillain and deranged psychiatrist who uses fear-inducing toxins to terrorize Gotham City.
  • D. Joe Shuster
    Joe Shuster was a Canadian-American comic book artist best known as the co-creator of Superman, one of the most iconic superheroes in popular culture.
  • E. Owen Harper
    Owen Harper is a central character in the British sci-fi series "Torchwood," serving as the team's acerbic and brilliant medical officer.
  • 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: Brainiac
Triple: [Superman, enemy, Brainiac]
Generated description
Brainiac is a highly intelligent and malevolent alien android in DC Comics, known for shrinking and collecting cities and serving as one of Superman’s most formidable foes.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Brainiac
Target entity description: Brainiac is a highly intelligent and malevolent alien android in DC Comics, known for shrinking and collecting cities and serving as one of Superman’s most formidable foes.
  • A. John Battsek
    John Battsek is a British film producer renowned for his work on acclaimed feature documentaries and sports-related non-fiction films.
  • B. Johnny Wadd
    Johnny Wadd is the fictional hardboiled detective character famously portrayed by adult film actor John Holmes in a series of 1970s pornographic films.
  • C. Scarecrow
    Scarecrow is a Batman supervillain and deranged psychiatrist who uses fear-inducing toxins to terrorize Gotham City.
  • D. Joe Shuster
    Joe Shuster was a Canadian-American comic book artist best known as the co-creator of Superman, one of the most iconic superheroes in popular culture.
  • E. Owen Harper
    Owen Harper is a central character in the British sci-fi series "Torchwood," serving as the team's acerbic and brilliant medical officer.
  • 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_69bd43d175248190894dc58b5b395c26 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd56ff78748190bb667e70c69dc817 completed March 20, 2026, 2:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69bd6f9d05d08190bde36e7d614a0e2e completed March 20, 2026, 4:02 p.m.
NEDg Description generation batch_69bd705e0e848190a73e7ddb569f0e37 completed March 20, 2026, 4:05 p.m.
NED2 Entity disambiguation (via description) batch_69bd71b41664819091bd4f75d4634943 completed March 20, 2026, 4:11 p.m.
Created at: March 20, 2026, 1:01 p.m.