Triple

T14641980
Position Surface form Disambiguated ID Type / Status
Subject Gerald Tommaso DeLouise E343745 entity
Predicate notableWork P4 FINISHED
Object Mickey Blue Eyes E840497 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: Mickey Blue Eyes | Statement: [Gerald Tommaso DeLouise, notableWork, Mickey Blue Eyes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mickey Blue Eyes
Context triple: [Gerald Tommaso DeLouise, notableWork, Mickey Blue Eyes]
  • A. Mickey Blue Eyes chosen
    Mickey Blue Eyes is a 1999 romantic comedy film starring Hugh Grant as an English auctioneer who becomes entangled with the New York Mafia through his fiancée’s family.
  • B. Mickey One
    Mickey One is a 1965 avant-garde crime drama film starring Warren Beatty as a paranoid stand-up comic on the run from the mob.
  • C. Mickey
    Mickey is the nickname of English actress Mickey Sumner, known for her roles in film and television such as "Frances Ha" and "Snowpiercer."
  • D. Mickey
    Mickey is the nickname of Gordon "Mickey" Cochrane, a Hall of Fame American Major League Baseball catcher and manager from the early 20th century.
  • E. Mickey
    Mickey is a themed parking section within the Mickey & Friends Parking Structure at the Disneyland Resort, named after Mickey Mouse.
  • 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_69d822e1a2cc81908e5bb93cf61ce3cc completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb4e80aa48190884bab800f357106 completed April 14, 2026, 9:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69fdd5d404e881908d26e684702ae122 completed May 8, 2026, 12:23 p.m.
Created at: April 10, 2026, 1:26 a.m.