Triple

T1107888
Position Surface form Disambiguated ID Type / Status
Subject Mary Poppins Returns E25527 entity
Predicate producer P490 FINISHED
Object John DeLuca E165233 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: John DeLuca | Statement: [Mary Poppins Returns, producer, John DeLuca]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John DeLuca
Context triple: [Mary Poppins Returns, producer, John DeLuca]
  • A. Greg Corrado
    Greg Corrado is an American computer scientist and researcher known for his pioneering work in artificial intelligence and deep learning, including co-founding Google Brain.
  • B. Gene Steratore
    Gene Steratore is a former NFL and NCAA football official best known as a longtime NFL referee and later rules analyst for CBS Sports.
  • C. Paul Merolla
    Paul Merolla is a neuroscientist and engineer best known as a co-founder of Neuralink, the neurotechnology company developing brain–computer interfaces.
  • D. Michael De Luca chosen
    Michael De Luca is an American film producer and studio executive known for overseeing and producing a wide range of major Hollywood films across genres.
  • E. John Cioffi
    John Cioffi is an American electrical engineer and Stanford professor emeritus renowned as the "father of DSL" for his pioneering work in high-speed digital communications over telephone lines.
  • 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_69a49428d4448190b3b36991ceae87ce completed March 1, 2026, 7:31 p.m.
NER Named-entity recognition batch_69a4b9e47e4881908928900df72781f0 completed March 1, 2026, 10:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69ad607966748190a5661d47021bf526 completed March 8, 2026, 11:41 a.m.
Created at: March 1, 2026, 7:43 p.m.