Triple

T18305897
Position Surface form Disambiguated ID Type / Status
Subject Kay Lake E438481 entity
Predicate portrayedBy P1507 FINISHED
Object Scarlett Johansson 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: Scarlett Johansson | Statement: [Kay Lake, portrayedBy, Scarlett Johansson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Scarlett Johansson
Context triple: [Kay Lake, portrayedBy, Scarlett Johansson]
  • A. Scarlett Johansson chosen
    Scarlett Johansson is an American actress known for her versatile film roles, including major parts in the Marvel Cinematic Universe and acclaimed performances in both independent and blockbuster movies.
  • B. Brie Larson
    Brie Larson is an Academy Award–winning American actress known for her versatile performances in films such as Room, Captain Marvel, and Kong: Skull Island.
  • C. Jess Wasikowska
    Jess Wasikowska is a sibling of Australian actress Mia Wasikowska, known for her role in films such as "Alice in Wonderland."
  • D. Marzen Wasikowska
    Marzen Wasikowska is the mother of Australian actress Mia Wasikowska.
  • E. Hayley Atwell
    Hayley Atwell is a British-American actress best known for portraying Peggy Carter in the Marvel Cinematic Universe.
  • 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_69d8b915e3e881909125d760c15d0c29 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e50183394081909b86cefaaa0a3aa8 completed April 19, 2026, 4:23 p.m.
Created at: April 10, 2026, 10:35 a.m.