Triple

T3673028
Position Surface form Disambiguated ID Type / Status
Subject Quick Change E77922 entity
Predicate coDirector P17194 FINISHED
Object Howard Franklin E285305 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: Howard Franklin | Statement: [Quick Change, coDirector, Howard Franklin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Howard Franklin
Context triple: [Quick Change, coDirector, 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. 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.
  • D. Frank Oliver Howard
    Frank Oliver Howard is the full name of Frank Howard, a notable American Major League Baseball slugger and outfielder/first baseman who played primarily in the 1960s and early 1970s.
  • E. Franklin Martin
    Franklin Martin was an American physician and medical leader best known for founding the American Cancer Society.
  • 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_69ad85e083008190b2e1b7085fe500bd completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc42f82548190b4d5f0fe7250decb completed March 8, 2026, 6:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4cde628c08190adc058d8d35a5e5d completed March 14, 2026, 2:54 a.m.
Created at: March 8, 2026, 3:25 p.m.