Triple

T2117583
Position Surface form Disambiguated ID Type / Status
Subject Lorne Michaels E43842 entity
Predicate founded P104 FINISHED
Object Broadway Video E43692 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: Broadway Video | Statement: [Lorne Michaels, founded, Broadway Video]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Broadway Video
Context triple: [Lorne Michaels, founded, Broadway Video]
  • A. Broadway Video chosen
    Broadway Video is a New York–based television and film production company best known for producing "Saturday Night Live" and other comedy programming.
  • B. Broadway
    Broadway is a subway station in South Boston on the Massachusetts Bay Transportation Authority (MBTA) system, providing access to the surrounding residential and commercial neighborhoods.
  • C. Broadway
    Broadway is a picturesque English village in Worcestershire’s Cotswolds, known for its honey-colored stone buildings, historic High Street, and role as a popular tourist destination.
  • D. Broadway
    Broadway is a major thoroughfare in New York City famous for its historic theaters and role as the heart of American commercial theater.
  • E. Broadway
    Broadway is a major thoroughfare in Cambridge, Massachusetts, running through the city center and connecting key academic, residential, and commercial areas.
  • 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_69a88717cfe48190b7ecdd68c824848a completed March 4, 2026, 7:25 p.m.
NER Named-entity recognition batch_69abbb2f6f608190937889bb393fe7c6 completed March 7, 2026, 5:44 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae5194abec8190aab8b7a9ef98da92 completed March 9, 2026, 4:50 a.m.
Created at: March 4, 2026, 7:43 p.m.