Triple

T4983537
Position Surface form Disambiguated ID Type / Status
Subject Glynis Johns E111945 entity
Predicate notableWork P4 FINISHED
Object The Ref
The Ref is a 1994 dark comedy film in which a burglar is forced to mediate a bickering couple’s marital problems on Christmas Eve.
E485722 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: The Ref | Statement: [Glynis Johns, notableWork, The Ref]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: The Ref
Context triple: [Glynis Johns, notableWork, The Ref]
  • A. The Referee
    The Referee is the official in association football responsible for enforcing the Laws of the Game, making decisions on play, and maintaining order on the field.
  • B. The Fan
    The Fan is a 1996 psychological thriller film about an obsessive baseball fan whose fixation on his favorite player turns dangerously violent.
  • C. The Fan
    The Fan is the popular nickname for Beijing's National Indoor Stadium, a major multi-purpose arena known for hosting events during the 2008 and 2022 Olympic Games.
  • D. Ballin
    "Ballin" is a track by Snoop Dogg from his 2002 album "Paid tha Cost to Be da Boss," showcasing his signature West Coast hip-hop style.
  • E. The Joe
    The Joe is a famous indoor arena in Detroit, Michigan, best known as the longtime home of the NHL’s Detroit Red Wings.
  • 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: The Ref
Triple: [Glynis Johns, notableWork, The Ref]
Generated description
The Ref is a 1994 dark comedy film in which a burglar is forced to mediate a bickering couple’s marital problems on Christmas Eve.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: The Ref
Target entity description: The Ref is a 1994 dark comedy film in which a burglar is forced to mediate a bickering couple’s marital problems on Christmas Eve.
  • A. The Referee
    The Referee is the official in association football responsible for enforcing the Laws of the Game, making decisions on play, and maintaining order on the field.
  • B. The Fan
    The Fan is a 1996 psychological thriller film about an obsessive baseball fan whose fixation on his favorite player turns dangerously violent.
  • C. The Fan
    The Fan is the popular nickname for Beijing's National Indoor Stadium, a major multi-purpose arena known for hosting events during the 2008 and 2022 Olympic Games.
  • D. Ballin
    "Ballin" is a track by Snoop Dogg from his 2002 album "Paid tha Cost to Be da Boss," showcasing his signature West Coast hip-hop style.
  • E. The Joe
    The Joe is a famous indoor arena in Detroit, Michigan, best known as the longtime home of the NHL’s Detroit Red Wings.
  • 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_69bd441adc208190b70a033a0741d01e completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd7255d7b4819098b537df5b1a4c3c completed March 20, 2026, 4:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69be8a13f5448190a49f914d1ba49a7a completed March 21, 2026, 12:07 p.m.
NEDg Description generation batch_69be8a9c72848190978797a33d0d83c8 completed March 21, 2026, 12:10 p.m.
NED2 Entity disambiguation (via description) batch_69be8b3718288190b2fc319fdad0a7c0 completed March 21, 2026, 12:12 p.m.
Created at: March 20, 2026, 1:33 p.m.