Triple

T19416228
Position Surface form Disambiguated ID Type / Status
Subject The Ref E485722 entity
Predicate mainCharacter P1183 FINISHED
Object Gus
Gus is the central character in the 1994 dark comedy film "The Ref," a sarcastic and beleaguered cat burglar who ends up taking a dysfunctional family hostage on Christmas Eve.
E1374938 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: Gus | Statement: [The Ref, mainCharacter, Gus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gus
Context triple: [The Ref, mainCharacter, Gus]
  • A. Gus
    Gus is the lovable, chubby mouse in Disney's 1950 animated film "Cinderella," known for his comic relief and loyal friendship to Cinderella.
  • B. Gus
    Gus is the given name of American filmmaker Gus Van Sant, known for directing independent and mainstream films such as "Good Will Hunting" and "Milk."
  • C. Gus
    Gus is the nickname of Virgil "Gus" Grissom, one of NASA's original Mercury Seven astronauts and a pioneering American spacefarer.
  • D. Gus
    Gus is a 1976 Disney sports comedy film about a football team that gains an unlikely advantage from a field-goal-kicking mule.
  • E. Gus
    Gus is one of the two hitmen at the center of Harold Pinter’s play "The Dumb Waiter," known for his anxious, questioning nature and tense exchanges in the basement setting.
  • 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: Gus
Triple: [The Ref, mainCharacter, Gus]
Generated description
Gus is the central character in the 1994 dark comedy film "The Ref," a sarcastic and beleaguered cat burglar who ends up taking a dysfunctional family hostage on Christmas Eve.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Gus
Target entity description: Gus is the central character in the 1994 dark comedy film "The Ref," a sarcastic and beleaguered cat burglar who ends up taking a dysfunctional family hostage on Christmas Eve.
  • A. Gus
    Gus is the lovable, chubby mouse in Disney's 1950 animated film "Cinderella," known for his comic relief and loyal friendship to Cinderella.
  • B. Gus
    Gus is the affectionate nickname of Burton "Gus" Guster, the loyal and often cautious best friend and business partner in the TV series "Psych."
  • C. Gus
    Gus is a 1976 Disney sports comedy film about a football team that gains an unlikely advantage from a field-goal-kicking mule.
  • D. Gus
    Gus is one of the two hitmen at the center of Harold Pinter’s play "The Dumb Waiter," known for his anxious, questioning nature and tense exchanges in the basement setting.
  • E. Gus
    Gus is the lonely but gentle gray cloud in Pixar’s short film "Partly Cloudy," known for creating dangerous baby animals for his stork partner to deliver.
  • 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_69d8e8d688f881909c85104a62e09d8a completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e62af9c8fc81909860de10b6720207 completed April 20, 2026, 1:32 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0733ce2e6081909e8baebf638747f1 completed May 15, 2026, 2:55 p.m.
NEDg Description generation batch_6a0734cfc2488190a488c40431a0b612 completed May 15, 2026, 2:59 p.m.
NED2 Entity disambiguation (via description) batch_6a0735c38b7881908489916ff2f2883e completed May 15, 2026, 3:03 p.m.
Created at: April 10, 2026, 1:37 p.m.