Triple

T7860808
Position Surface form Disambiguated ID Type / Status
Subject Catherine Hughes E182491 entity
Predicate hasRelative P367 FINISHED
Object Helen Hughes E261299 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 Hughes | Statement: [Catherine Hughes, hasRelative, Helen Hughes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Helen Hughes
Context triple: [Catherine Hughes, hasRelative, Helen Hughes]
  • A. Helen Hughes chosen
    Helen Hughes was a daughter of Charles Evans Hughes, the prominent American statesman who served as both U.S. Secretary of State and Chief Justice of the Supreme Court.
  • B. Helen Wright
    Helen Wright is a wealthy, emotionally volatile socialite who becomes romantically entangled with a young violin prodigy in the film "Humoresque."
  • C. Helen Ferguson
    Helen Ferguson was an American silent film actress prominent in the 1910s and 1920s who later became a successful Hollywood publicist.
  • D. Helen Ferguson
    Helen Ferguson is a secondary character in Ernest Hemingway's novel "A Farewell to Arms," serving as Catherine Barkley's protective friend and a skeptical observer of her relationship with Frederic Henry.
  • E. Helen Harrington
    Helen Harrington is known as the wife of American minimalist painter Brice Marden.
  • 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_69ca82887fd48190975896bf38c4596b completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb36bcb5cc8190a8a384ce0f020b9f completed March 31, 2026, 2:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69d32a1e1de88190a98ce4b6aea1a148 completed April 6, 2026, 3:35 a.m.
Created at: March 30, 2026, 4:53 p.m.