Triple

T18731510
Position Surface form Disambiguated ID Type / Status
Subject Martha Marcy May Marlene E458044 entity
Predicate starredActor P5563 FINISHED
Object Elizabeth Olsen 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: Elizabeth Olsen | Statement: [Martha Marcy May Marlene, starredActor, Elizabeth Olsen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Elizabeth Olsen
Context triple: [Martha Marcy May Marlene, starredActor, Elizabeth Olsen]
  • A. Elizabeth Olsen chosen
    Elizabeth Olsen is an American actress best known for portraying Wanda Maximoff / Scarlet Witch in the Marvel Cinematic Universe.
  • B. Hayley Atwell
    Hayley Atwell is a British-American actress best known for portraying Peggy Carter in the Marvel Cinematic Universe.
  • C. Carrie Snodgress
    Carrie Snodgress was an American actress best known for her Oscar-nominated role in "Diary of a Mad Housewife" and her work in film and television during the 1970s and 1980s.
  • D. Tessa Thompson
    Tessa Thompson is an American actress known for her versatile performances in film and television, including prominent roles in projects like "Creed," "Thor: Ragnarok," and "Westworld."
  • E. 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.
  • 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_69d8d393ba9c8190a8b03b04ddbb0a09 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e56d7854748190b66c4aaadfd67f29 completed April 20, 2026, 12:04 a.m.
Created at: April 10, 2026, 11:51 a.m.