Triple

T21398931
Position Surface form Disambiguated ID Type / Status
Subject Brute Force E527859 entity
Predicate starring P1507 FINISHED
Object Howard Duff 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: Howard Duff | Statement: [Brute Force, starring, Howard Duff]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Howard Duff
Context triple: [Brute Force, starring, Howard Duff]
  • A. Howard Duff chosen
    Howard Duff was an American actor known for his work in film, radio, and television, including notable roles in classic noir and mid-20th-century dramas.
  • B. June Winchell
    June Winchell was the wife of influential American newspaper and radio gossip columnist Walter Winchell.
  • C. Truman Seymour
    Truman Seymour was a Union Army general and career U.S. Army officer who served in the Mexican–American War, the American Civil War, and later as an artist.
  • D. Hamilton MacFadden
    Hamilton MacFadden was an American film director and actor active in early Hollywood, known for his work in the 1930s studio system.
  • E. Broderick Crawford
    Broderick Crawford was an American actor best known for his Academy Award-winning role in the film "All the King's Men" and for starring in the television series "Highway Patrol."
  • 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_69e0b520ee3c8190abddbee7e37e834c completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69ee62cf3e808190847ad66d2e65f9f2 completed April 26, 2026, 7:09 p.m.
Created at: April 16, 2026, 5:14 p.m.