Triple

T20541122
Position Surface form Disambiguated ID Type / Status
Subject Benn W. Levy E504334 entity
Predicate notableWork P4 FINISHED
Object Cluny Brown NE NERFINISHED

How this triple was built (2 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: Cluny Brown | Statement: [Benn W. Levy, notableWork, Cluny Brown]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cluny Brown
Context triple: [Benn W. Levy, notableWork, Cluny Brown]
  • A. Cluny Brown chosen
    Cluny Brown is a 1946 romantic comedy film directed by Ernst Lubitsch, known for its witty social satire and the story of an unconventional young woman who challenges British class norms.
  • B. Maria Shireburn
    Maria Shireburn was an English Catholic noblewoman and heiress of the Shireburn family, best known for her prominent position in Jacobite aristocratic circles in the early 18th century.
  • C. Catherine Oliphant
    Catherine Oliphant is a fictional character in Barbara Pym’s novel "Less Than Angels," depicted as an observant, witty writer navigating academic and romantic entanglements in postwar London.
  • D. Marjory
    Marjory is a feminine given name, commonly considered a variant spelling of Marjorie.
  • E. Isa Knox
    Isa Knox is a South Korean beauty and skincare brand known for its anti-aging and premium cosmetic products.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b4b476648190bc6019622ae54d3c completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a29224f081908298d104161c5bb9 completed April 20, 2026, 10:02 p.m.
Created at: April 16, 2026, 11:37 a.m.