Triple

T1009861
Position Surface form Disambiguated ID Type / Status
Subject Sophie Thompson E21796 entity
Predicate notableWork P4 FINISHED
Object Persuasion
"Persuasion" is a television film adaptation of Jane Austen's novel, featuring Sophie Thompson in a prominent role.
 E120706 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: Persuasion | Statement: [Sophie Thompson, notableWork, Persuasion]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Persuasion
Context triple: [Sophie Thompson, notableWork, Persuasion]
  • A. Sense and Sensibility
    Sense and Sensibility is a 1995 British period drama film adaptation of Jane Austen’s novel, acclaimed for its screenplay by and starring Emma Thompson.
  • B. Dashwood
    Dashwood is the surname of the central family in Jane Austen's novel "Sense and Sensibility," including the character Elinor Dashwood.
  • C. So Long, Marianne
    "So Long, Marianne" is a classic Leonard Cohen song, celebrated as one of his most enduring and intimate folk ballads about love and separation.
  • D. Vanity Fair
    Vanity Fair is a popular American brand of premium paper products, particularly known for its napkins and tableware.
  • E. Catherine
    Catherine is a feminine given name of Greek origin, derived from Aikaterine and widely used in various forms across many cultures.
  • 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: Persuasion
Triple: [Sophie Thompson, notableWork, Persuasion]
Generated description
"Persuasion" is a television film adaptation of Jane Austen's novel, featuring Sophie Thompson in a prominent role.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Persuasion
Target entity description: "Persuasion" is a television film adaptation of Jane Austen's novel, featuring Sophie Thompson in a prominent role.
  • A. Sense and Sensibility
    Sense and Sensibility is a 1995 British period drama film adaptation of Jane Austen’s novel, acclaimed for its screenplay by and starring Emma Thompson.
  • B. Dashwood
    Dashwood is the surname of the central family in Jane Austen's novel "Sense and Sensibility," including the character Elinor Dashwood.
  • C. So Long, Marianne
    "So Long, Marianne" is a classic Leonard Cohen song, celebrated as one of his most enduring and intimate folk ballads about love and separation.
  • D. Vanity Fair
    Vanity Fair is a popular American brand of premium paper products, particularly known for its napkins and tableware.
  • E. Catherine
    Catherine is a feminine given name of Greek origin, derived from Aikaterine and widely used in various forms across many cultures.
  • 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_69a493c53e648190ae8cb76c433fd9a7 completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4b7a3cb608190a2de34a09cd55146 completed March 1, 2026, 10:03 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac3bab71388190ba8bbfd79a5e0f92 completed March 7, 2026, 2:52 p.m.
NEDg Description generation batch_69ac3c30311081909e817de7cf9c2d9b completed March 7, 2026, 2:54 p.m.
NED2 Entity disambiguation (via description) batch_69ac3c9cc1ec819087df1f4c4efc5646 completed March 7, 2026, 2:56 p.m.
Created at: March 1, 2026, 7:41 p.m.