Triple

T10810752
Position Surface form Disambiguated ID Type / Status
Subject Tea for Two E255092 entity
Predicate screenwriter P2831 FINISHED
Object Harry Clork
Harry Clork was an American screenwriter active during Hollywood’s classic era, known for contributing to numerous studio comedies and musicals.
E887366 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: Harry Clork | Statement: [Tea for Two, screenwriter, Harry Clork]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harry Clork
Context triple: [Tea for Two, screenwriter, Harry Clork]
  • A. Harry Compton
    Harry Compton is a fictional character from the 1940 American film "Boom Town," which centers on the lives and rivalries of wildcat oil drillers.
  • B. Gerald Lathbury
    Gerald Lathbury was a British Army lieutenant general and distinguished airborne commander during the Second World War.
  • C. Harry Peacock
    Harry Peacock is a British actor known for his work in television comedies and dramas, and as the son of actor and songwriter Trevor Peacock.
  • D. Harry Lonsdale
    Harry Lonsdale was an early 20th-century actor known for his roles in silent films.
  • E. Harry Bertram
    Harry Bertram is the long-lost heir whose disappearance and eventual restoration to his family’s estate drive the central plot of Sir Walter Scott’s novel "Guy Mannering."
  • 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: Harry Clork
Triple: [Tea for Two, screenwriter, Harry Clork]
Generated description
Harry Clork was an American screenwriter active during Hollywood’s classic era, known for contributing to numerous studio comedies and musicals.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Harry Clork
Target entity description: Harry Clork was an American screenwriter active during Hollywood’s classic era, known for contributing to numerous studio comedies and musicals.
  • A. Harry Compton
    Harry Compton is a fictional character from the 1940 American film "Boom Town," which centers on the lives and rivalries of wildcat oil drillers.
  • B. Gerald Lathbury
    Gerald Lathbury was a British Army lieutenant general and distinguished airborne commander during the Second World War.
  • C. Harry Peacock
    Harry Peacock is a British actor known for his work in television comedies and dramas, and as the son of actor and songwriter Trevor Peacock.
  • D. Harry Lonsdale
    Harry Lonsdale was an early 20th-century actor known for his roles in silent films.
  • E. Harry Bertram
    Harry Bertram is the long-lost heir whose disappearance and eventual restoration to his family’s estate drive the central plot of Sir Walter Scott’s novel "Guy Mannering."
  • 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_69d6aa61c15c8190a1839550c56e75e1 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d733b7bfac8190b6ae34144376d6ad completed April 9, 2026, 5:05 a.m.
NED1 Entity disambiguation (via context triple) batch_69de8526237881908dc3b25b16de7871 completed April 14, 2026, 6:19 p.m.
NEDg Description generation batch_69de8954500c81909b57c4f8007959aa completed April 14, 2026, 6:37 p.m.
NED2 Entity disambiguation (via description) batch_69de8f38e3048190b1acc81bb56fe165 completed April 14, 2026, 7:02 p.m.
Created at: April 8, 2026, 9:18 p.m.