Triple

T20407494
Position Surface form Disambiguated ID Type / Status
Subject Sam Peckinpah E500508 entity
Predicate spouse P13 FINISHED
Object Marie Selland 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: Marie Selland | Statement: [Sam Peckinpah, spouse, Marie Selland]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marie Selland
Context triple: [Sam Peckinpah, spouse, Marie Selland]
  • A. Marie Selland chosen
    Marie Selland was the first wife of American film director Sam Peckinpah, known primarily in relation to his early personal life.
  • B. Marie Serneholt
    Marie Serneholt is a Swedish pop singer and television presenter best known as a former member of the teen pop group A-Teens.
  • C. Marie Nygren
    Marie Nygren is an American entrepreneur and community developer best known as a co-founder of Serenbe, a pioneering sustainable, wellness-focused community in Georgia.
  • D. Marie Lohr
    Marie Lohr was an English actress known for her stage and film work in the early 20th century, often appearing in British dramas and literary adaptations.
  • E. Marie Ledin
    Marie Ledin is a Swedish music industry executive and former singer who has led the Polar Music Prize organization and worked extensively in music publishing and record production.
  • 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_69e0b4a81bec8190b69adfdc1336a015 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e67993dc7081908ebd54ec92e712ea completed April 20, 2026, 7:08 p.m.
Created at: April 16, 2026, 11:29 a.m.