Triple

T9482220
Position Surface form Disambiguated ID Type / Status
Subject Kate Soffel E228669 entity
Predicate basedOnRealPersonIn P86334 FINISHED
Object "Mrs. Soffel" (1984 film)
"Mrs. Soffel" is a 1984 period drama film starring Diane Keaton as a warden’s wife who falls in love with a condemned prisoner and helps him escape, inspired by a real-life early 20th-century prison break.
E802498 NE FINISHED

How this triple was built (5 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: "Mrs. Soffel" (1984 film) | Statement: [Kate Soffel, basedOnRealPersonIn, "Mrs. Soffel" (1984 film)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: "Mrs. Soffel" (1984 film)
Context triple: [Kate Soffel, basedOnRealPersonIn, "Mrs. Soffel" (1984 film)]
  • A. An Unmarried Woman
    An Unmarried Woman is a 1978 American drama film written and directed by Paul Mazursky that follows a New York woman’s journey of self-discovery after her husband leaves her, noted for its feminist themes and Jill Clayburgh’s acclaimed performance.
  • B. Office Romance (1977 film)
    Office Romance (1977 film) is a beloved Soviet romantic comedy directed by Eldar Ryazanov that humorously explores love and relationships among co-workers in a Moscow statistics bureau.
  • C. Frances (1982 film)
    Frances (1982 film) is a biographical drama chronicling the turbulent life, career, and institutionalization of American actress Frances Farmer.
  • D. Mary Hartman, Mary Hartman
    Mary Hartman, Mary Hartman is a satirical 1970s American television soap opera known for its dark humor and critique of suburban life and consumer culture.
  • E. Working Girl
    Working Girl is a 1988 romantic comedy-drama film about an ambitious secretary navigating corporate New York, directed by Mike Nichols and starring Melanie Griffith, Harrison Ford, and Sigourney Weaver.
  • 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: "Mrs. Soffel" (1984 film)
Triple: [Kate Soffel, basedOnRealPersonIn, "Mrs. Soffel" (1984 film)]
Generated description
"Mrs. Soffel" is a 1984 period drama film starring Diane Keaton as a warden’s wife who falls in love with a condemned prisoner and helps him escape, inspired by a real-life early 20th-century prison break.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: "Mrs. Soffel" (1984 film)
Target entity description: "Mrs. Soffel" is a 1984 period drama film starring Diane Keaton as a warden’s wife who falls in love with a condemned prisoner and helps him escape, inspired by a real-life early 20th-century prison break.
  • A. An Unmarried Woman
    An Unmarried Woman is a 1978 American drama film written and directed by Paul Mazursky that follows a New York woman’s journey of self-discovery after her husband leaves her, noted for its feminist themes and Jill Clayburgh’s acclaimed performance.
  • B. Office Romance (1977 film)
    Office Romance (1977 film) is a beloved Soviet romantic comedy directed by Eldar Ryazanov that humorously explores love and relationships among co-workers in a Moscow statistics bureau.
  • C. Frances (1982 film)
    Frances (1982 film) is a biographical drama chronicling the turbulent life, career, and institutionalization of American actress Frances Farmer.
  • D. Mary Hartman, Mary Hartman
    Mary Hartman, Mary Hartman is a satirical 1970s American television soap opera known for its dark humor and critique of suburban life and consumer culture.
  • E. Working Girl
    Working Girl is a 1988 romantic comedy-drama film about an ambitious secretary navigating corporate New York, directed by Mike Nichols and starring Melanie Griffith, Harrison Ford, and Sigourney Weaver.
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: basedOnRealPersonIn
Context triple: [Kate Soffel, basedOnRealPersonIn, "Mrs. Soffel" (1984 film)]
  • A. basedOnRealPersonFor
    Indicates that one entity is created, modeled, or inspired using a specific real person as its basis.
  • B. characterRealWorldCounterpart chosen
    Indicates that a fictional character is based on, inspired by, or directly corresponds to a specific real-world person.
  • C. basedOnRealLocation
    Indicates that something is derived from, inspired by, or modeled after an actual geographic place in the real world.
  • D. hasPersona
    Indicates that an entity possesses or is associated with a particular persona, role, or character profile.
  • E. basedOnRealRegion
    Indicates that something is derived from, inspired by, or corresponds to an actual geographic or administrative region in the real world.
  • F. None of above.

Provenance (6 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_69ca84730a5081908de282651019bf2f completed March 30, 2026, 2:10 p.m.
NER Named-entity recognition batch_69cd804af6d08190a281cb27407c791c completed April 1, 2026, 8:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69d12d0620608190a6697777ec2eec26 completed April 4, 2026, 3:23 p.m.
NEDg Description generation batch_69d12db5c20881909a7011a3d25dd2b8 completed April 4, 2026, 3:26 p.m.
NED2 Entity disambiguation (via description) batch_69d12e4f1b9081908e73aa674d1ef0e4 completed April 4, 2026, 3:29 p.m.
PD Predicate disambiguation batch_69cca561e6b0819090aa795f3c3a2083 completed April 1, 2026, 4:56 a.m.
Created at: March 30, 2026, 7:55 p.m.