Triple

T7354822
Position Surface form Disambiguated ID Type / Status
Subject Max Dugan Returns E169595 entity
Predicate starring P1507 FINISHED
Object Marsha Mason E524539 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: Marsha Mason | Statement: [Max Dugan Returns, starring, Marsha Mason]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marsha Mason
Context triple: [Max Dugan Returns, starring, Marsha Mason]
  • A. Marsha Mason chosen
    Marsha Mason is an American actress known for her acclaimed film and stage work, including multiple Academy Award–nominated performances in 1970s and 1980s dramas and romantic comedies.
  • B. Mary Bellingham
    Mary Bellingham was the wife of John Bellingham, the man infamous for assassinating British Prime Minister Spencer Perceval in 1812.
  • C. Patricia Clarkson
    Patricia Clarkson is an American actress acclaimed for her versatile performances in film, television, and theater, often in complex supporting roles.
  • D. Anna Massey
    Anna Massey was an acclaimed English actress known for her nuanced performances in film, television, and theatre, including notable roles in psychological dramas and literary adaptations.
  • E. Anne Rennie
    Anne Rennie is known as the wife of bestselling adventure novelist Wilbur Smith.
  • 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_69c68a59f2288190877ca15c19b1e822 completed March 27, 2026, 1:47 p.m.
NER Named-entity recognition batch_69c6f10e71fc81909307ca39a61142d3 completed March 27, 2026, 9:05 p.m.
NED1 Entity disambiguation (via context triple) batch_69c845e46d4881909b346391812513a2 completed March 28, 2026, 9:19 p.m.
Created at: March 27, 2026, 3:05 p.m.