Triple

T20701613
Position Surface form Disambiguated ID Type / Status
Subject I Love You Phillip Morris E508796 entity
Predicate castMember P1668 FINISHED
Object Leslie Mann NE NERFINISHED

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: Leslie Mann | Statement: [I Love You Phillip Morris, castMember, Leslie Mann]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Leslie Mann
Context triple: [I Love You Phillip Morris, castMember, Leslie Mann]
  • A. Leslie Mann chosen
    Leslie Mann is an American actress known for her comedic and dramatic roles in films such as "The 40-Year-Old Virgin," "Knocked Up," and "This Is 40."
  • B. Amanda Peet
    Amanda Peet is an American actress known for her work in films like "The Whole Nine Yards" and television series such as "Studio 60 on the Sunset Strip" and "Togetherness."
  • C. Alison Lohman
    Alison Lohman is an American actress known for her roles in films such as Big Fish, White Oleander, and Drag Me to Hell.
  • D. Judy Greer
    Judy Greer is an American actress known for her versatile supporting roles in film and television, including appearances in major franchises like the Marvel Cinematic Universe.
  • E. Michaela Watkins
    Michaela Watkins is an American actress and comedian known for her work on "Saturday Night Live" and in numerous television comedies and films.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69e0b4c2b2a481909e31e9cb8f81ab55 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6c18bfac08190bf80beeb3ce1951a completed April 21, 2026, 12:15 a.m.
Created at: April 16, 2026, 12:12 p.m.