Triple

T14622598
Position Surface form Disambiguated ID Type / Status
Subject MJ E343260 entity
Predicate friendOf P8712 FINISHED
Object Ned Leeds E820271 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: Ned Leeds | Statement: [MJ, friendOf, Ned Leeds]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ned Leeds
Context triple: [MJ, friendOf, Ned Leeds]
  • A. Ned Leeds chosen
    Ned Leeds is Peter Parker’s best friend and comic-relief sidekick in the Marvel Cinematic Universe, known for his enthusiastic support of Spider-Man and his humorous, nerdy personality.
  • B. Eric Leeds
    Eric Leeds is an American saxophonist and composer best known for his long-time collaboration with Prince across projects like The New Power Generation and Madhouse.
  • C. Ned Ryerson
    Ned Ryerson is the overly enthusiastic insurance salesman and former classmate who repeatedly accosts Phil Connors in the film "Groundhog Day."
  • D. Eric Leach
    Eric Leach is a cinematographer best known for his work on the psychological thriller film "Enter Nowhere."
  • E. Ned Sherwood
    Ned Sherwood is the central protagonist of the 1957 film noir "The Big Boodle," a croupier who becomes entangled in a dangerous counterfeit money scheme in Havana.
  • 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_69d822dffc3c8190aa173b90761bffda completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb466a61c81908a110d40fb959b6f completed April 14, 2026, 9:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69fda9288e748190bf65a01803265a73 completed May 8, 2026, 9:13 a.m.
Created at: April 10, 2026, 1:25 a.m.