Triple

T18600888
Position Surface form Disambiguated ID Type / Status
Subject Richard Leacock E454615 entity
Predicate employer P7 FINISHED
Object MIT Film Section — NE NERFINISHED

How this triple was built (3 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: MIT Film Section | Statement: [Richard Leacock, employer, MIT Film Section]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: MIT Film Section
Context triple: [Richard Leacock, employer, MIT Film Section]
  • A. Maisha Film Lab
    Maisha Film Lab is a nonprofit training initiative in East Africa that nurtures emerging filmmakers through workshops, mentorship, and support for independent storytelling.
  • B. School of Filmmaking
    The School of Filmmaking is a specialized conservatory program dedicated to training students in the art and craft of motion picture production, including directing, screenwriting, cinematography, editing, and producing.
  • C. College of Film and the Moving Image
    The College of Film and the Moving Image is Wesleyan University’s renowned interdisciplinary hub for film studies, filmmaking, and related moving-image arts.
  • D. Graduate School of Film and New Media
    The Graduate School of Film and New Media is a specialized graduate institution of Tokyo University of the Arts dedicated to advanced education and research in film, animation, and related media arts.
  • E. UP Film Institute
    The UP Film Institute is the University of the Philippines Diliman’s premier center for film education, production, and scholarship, offering academic programs and serving as a hub for Philippine cinema.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: MIT Film Section
Target entity description: The MIT Film Section was an influential program at the Massachusetts Institute of Technology dedicated to innovative film production and education, particularly known for its role in the development of cinéma vérité and documentary filmmaking.
  • A. Maisha Film Lab
    Maisha Film Lab is a nonprofit training initiative in East Africa that nurtures emerging filmmakers through workshops, mentorship, and support for independent storytelling.
  • B. School of Filmmaking
    The School of Filmmaking is a specialized conservatory program dedicated to training students in the art and craft of motion picture production, including directing, screenwriting, cinematography, editing, and producing.
  • C. College of Film and the Moving Image
    The College of Film and the Moving Image is Wesleyan University’s renowned interdisciplinary hub for film studies, filmmaking, and related moving-image arts.
  • D. Graduate School of Film and New Media
    The Graduate School of Film and New Media is a specialized graduate institution of Tokyo University of the Arts dedicated to advanced education and research in film, animation, and related media arts.
  • E. UP Film Institute
    The UP Film Institute is the University of the Philippines Diliman’s premier center for film education, production, and scholarship, offering academic programs and serving as a hub for Philippine cinema.
  • F. None of above. chosen

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_69d8d38ae7e081908a98df1251842402 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e5475112608190acacc5ac7a08c4a0 completed April 19, 2026, 9:21 p.m.
Created at: April 10, 2026, 11:45 a.m.