Triple

T22102493
Position Surface form Disambiguated ID Type / Status
Subject The Public Eye E546204 entity
Predicate screenwriter P2831 FINISHED
Object Howard Franklin 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 Franklin | Statement: [The Public Eye, screenwriter, Howard Franklin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Howard Franklin
Context triple: [The Public Eye, screenwriter, Howard Franklin]
  • A. Howard Franklin chosen
    Howard Franklin is an American screenwriter and film director known for his work on movies such as "Quick Change" and "The Name of the Rose."
  • B. Peter Franklin
    Peter Franklin was one of Benjamin Franklin’s lesser-known siblings, a member of the large Franklin family in colonial New England.
  • C. Morris Franklin
    Morris Franklin was a 19th-century American lawyer and businessman best known for co-founding the Metropolitan Life Insurance Company.
  • D. Howard Holbrook
    Howard Holbrook is an individual notable enough to be recognized as a bearer of the Holbrook surname, though specific widely known public details about him are not readily established.
  • E. Howard Vollum
    Howard Vollum was an American engineer and entrepreneur best known as the co-founder of Tektronix, a pioneering company in oscilloscopes and electronic test equipment.
  • 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_69e11e378dc08190896d6a51597afd5a completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f129163b908190b63ace06016f4db8 completed April 28, 2026, 9:39 p.m.
Created at: April 16, 2026, 8:30 p.m.