Triple

T9836811
Position Surface form Disambiguated ID Type / Status
Subject Thunderbolt (1929 film) E239121 entity
Predicate editedBy P1954 FINISHED
Object Helen Lewis E824707 NE FINISHED

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: Helen Lewis | Statement: [Thunderbolt (1929 film), editedBy, Helen Lewis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Helen Lewis
Context triple: [Thunderbolt (1929 film), editedBy, Helen Lewis]
  • A. Helen Lewis chosen
    Helen Lewis was a film editor known for her work in early American cinema, including editing the 1928 silent drama "The Docks of New York."
  • B. Anne Leon
    Anne Leon is known as the spouse of English character actor Michael Gough, famed for his role as Alfred in the Batman film series.
  • C. Barbara Kyle
    Barbara Kyle is a British computer scientist known for her involvement in early work on programming language design and formal methods as part of the mid-20th-century UK computing community.
  • D. Fiona Hill
    Fiona Hill is a British-American foreign policy expert and former U.S. National Security Council official known for her expertise on Russia and her testimony in the first Trump impeachment inquiry.
  • E. Diana Woodward
    Diana Woodward is a daughter of renowned American investigative journalist Bob Woodward.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ca84e314108190978324a4bdb959f8 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cdb33b07688190b78a70cf535c3efc completed April 2, 2026, 12:07 a.m.
NED1 Entity disambiguation (via context triple) batch_69d1e423ba2c81909a46e56e2b004097 completed April 5, 2026, 4:25 a.m.
Created at: March 30, 2026, 8:33 p.m.