Triple

T20518078
Position Surface form Disambiguated ID Type / Status
Subject Harve Bennett E503731 entity
Predicate spouse P13 FINISHED
Object Caroline Bennett
Caroline Bennett is known as the wife of American television and film producer Harve Bennett.
 E1436045 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: Caroline Bennett | Statement: [Harve Bennett, spouse, Caroline Bennett]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Caroline Bennett
Context triple: [Harve Bennett, spouse, Caroline Bennett]
  • A. Kate Moseley
    Kate Moseley is the driven, once-elite figure skater character from the romantic sports film "The Cutting Edge."
  • B. Carole Cadwalladr
    Carole Cadwalladr is a British investigative journalist and author best known for her reporting on the Facebook–Cambridge Analytica data scandal and its impact on democracy.
  • C. Sarah Hilary
    Sarah Hilary is a British crime novelist best known for her Marnie Rome detective series and her contributions to contemporary crime fiction.
  • D. Verity Faulks
    Verity Faulks is the wife of British novelist Sebastian Faulks, known for maintaining a private life largely out of the public eye despite her husband's literary prominence.
  • E. Caroline Benn
    Caroline Benn was a prominent British educationalist and campaigner known for her advocacy of comprehensive education and social justice.
  • 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: Caroline Bennett
Triple: [Harve Bennett, spouse, Caroline Bennett]
Generated description
Caroline Bennett is known as the wife of American television and film producer Harve Bennett.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Caroline Bennett
Target entity description: Caroline Bennett is known as the wife of American television and film producer Harve Bennett.
  • A. Kate Moseley
    Kate Moseley is the driven, once-elite figure skater character from the romantic sports film "The Cutting Edge."
  • B. Carole Cadwalladr
    Carole Cadwalladr is a British investigative journalist and author best known for her reporting on the Facebook–Cambridge Analytica data scandal and its impact on democracy.
  • C. Sarah Hilary
    Sarah Hilary is a British crime novelist best known for her Marnie Rome detective series and her contributions to contemporary crime fiction.
  • D. Verity Faulks
    Verity Faulks is the wife of British novelist Sebastian Faulks, known for maintaining a private life largely out of the public eye despite her husband's literary prominence.
  • E. Caroline Benn
    Caroline Benn was a prominent British educationalist and campaigner known for her advocacy of comprehensive education and social justice.
  • 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_69e0b4b2aa788190ae9eb37c1d73b1f1 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e69f43e0b08190b043f35645b264a0 completed April 20, 2026, 9:48 p.m.
NED1 Entity disambiguation (via context triple) batch_6a089d3d55a08190b478b4b8f50ff101 completed May 16, 2026, 4:37 p.m.
NEDg Description generation batch_6a089e5816308190979cd7ab78a0c0f6 completed May 16, 2026, 4:42 p.m.
NED2 Entity disambiguation (via description) batch_6a089ecd0f988190afc859a511a18f7b completed May 16, 2026, 4:43 p.m.
Created at: April 16, 2026, 11:36 a.m.