Triple

T11498644
Position Surface form Disambiguated ID Type / Status
Subject Marilyn Bergman E272607 entity
Predicate familyName P18 FINISHED
Object Bergman E92338 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: Bergman | Statement: [Marilyn Bergman, familyName, Bergman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bergman
Context triple: [Marilyn Bergman, familyName, Bergman]
  • A. Bergman chosen
    Bergman is the surname of Ingrid Bergman, the acclaimed Swedish actress renowned for her roles in classic films such as "Casablanca" and "Notorious."
  • B. William Bergman
    William Bergman is an entrepreneur best known as the founder of the lip care and skincare brand Blistex.
  • C. Ingmar Bergman
    Ingmar Bergman was a renowned Swedish film and theatre director, screenwriter, and producer, celebrated for his psychologically intense and philosophically rich works such as "The Seventh Seal" and "Persona."
  • D. Schygulla
    Schygulla is a German surname most famously borne by actress Hanna Schygulla, a prominent figure in New German Cinema.
  • E. Hans Alfredson
    Hans Alfredson was a renowned Swedish comedian, actor, writer, and director, best known as one half of the influential comedy duo Hasse & Tage.
  • 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_69d6aae1b09881909ce2ded3fa0c14fa completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d85de27db081909ccdb4ab0ef75bdb completed April 10, 2026, 2:18 a.m.
NED1 Entity disambiguation (via context triple) batch_69e604aa9e3c8190ad86e4d05a67c8ac completed April 20, 2026, 10:49 a.m.
Created at: April 8, 2026, 9:36 p.m.