Triple

T23031790
Position Surface form Disambiguated ID Type / Status
Subject Johnny Tsunami E573479 entity
Predicate hasCharacter P2308 FINISHED
Object Randy
Randy is a supporting character in the Disney Channel Original Movie "Johnny Tsunami," appearing as part of the protagonist’s friend group in the film’s surfing and snowboarding-centered story.
 E1565987 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: Randy | Statement: [Johnny Tsunami, hasCharacter, Randy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Randy
Context triple: [Johnny Tsunami, hasCharacter, Randy]
  • A. Randy
    Randy is the nickname of Randy Moffitt, a former Major League Baseball relief pitcher best known for his long tenure with the San Francisco Giants in the 1970s.
  • B. Randy
    Randy is a mischievous, troublemaking marionette character from the children's television series "Pee-wee's Playhouse."
  • C. Randy
    Randy is a supporting character in the dark comedy film "The Opposite of Sex," involved in the tangled romantic and emotional conflicts that drive the story.
  • D. Randy
    Randy is a masculine given name commonly used in English-speaking countries, often as a diminutive of Randall or Randolph.
  • E. Randy Tack
    Randy Tack is an American local politician serving as the mayor of Lake Forest, Illinois.
  • 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: Randy
Triple: [Johnny Tsunami, hasCharacter, Randy]
Generated description
Randy is a supporting character in the Disney Channel Original Movie "Johnny Tsunami," appearing as part of the protagonist’s friend group in the film’s surfing and snowboarding-centered story.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Randy
Target entity description: Randy is a supporting character in the Disney Channel Original Movie "Johnny Tsunami," appearing as part of the protagonist’s friend group in the film’s surfing and snowboarding-centered story.
  • A. Randy
    Randy is a supporting character in the dark comedy film "The Opposite of Sex," involved in the tangled romantic and emotional conflicts that drive the story.
  • B. Randy
    Randy is the nickname of Randy Moffitt, a former Major League Baseball relief pitcher best known for his long tenure with the San Francisco Giants in the 1970s.
  • C. Randy
    Randy is a masculine given name commonly used in English-speaking countries, often as a diminutive of Randall or Randolph.
  • D. Randy
    Randy is a mischievous, troublemaking marionette character from the children's television series "Pee-wee's Playhouse."
  • E. Randy Tack
    Randy Tack is an American local politician serving as the mayor of Lake Forest, Illinois.
  • 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_69e245b911188190bc3d96326c847969 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f184822a90819081907d72c76770b0 completed April 29, 2026, 4:09 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0bf2b54b888190b1761586d2a2583a completed May 19, 2026, 5:18 a.m.
NEDg Description generation batch_6a0bf6f8ea048190af15e0494c19c6a1 completed May 19, 2026, 5:36 a.m.
NED2 Entity disambiguation (via description) batch_6a0bf76284988190ac4b8f08859aecc6 completed May 19, 2026, 5:38 a.m.
Created at: April 17, 2026, 3:53 p.m.