Triple

T18079631
Position Surface form Disambiguated ID Type / Status
Subject Elettra Rossellini Wiedemann E432651 entity
Predicate grandmother P3524 FINISHED
Object Ingrid Bergman 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: Ingrid Bergman | Statement: [Elettra Rossellini Wiedemann, grandmother, Ingrid Bergman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ingrid Bergman
Context triple: [Elettra Rossellini Wiedemann, grandmother, Ingrid Bergman]
  • A. Ingrid Bergman chosen
    Ingrid Bergman was an acclaimed Swedish actress and three-time Academy Award winner best known for her luminous performances in classic films such as "Casablanca" and "Notorious."
  • B. Eva Bergman
    Eva Bergman is a Swedish theatre and television director, known for her work on stage and screen and as the daughter of filmmaker Ingmar Bergman.
  • C. Ingrid Thulin
    Ingrid Thulin was a renowned Swedish actress best known for her intense, emotionally complex performances in several of Ingmar Bergman’s classic films.
  • D. Audrey Hepburn
    Audrey Hepburn was an iconic British actress and humanitarian, celebrated for her timeless style and roles in classic films such as "Breakfast at Tiffany's."
  • E. Luise Rainer
    Luise Rainer was a German-born American actress and two-time Academy Award winner in the 1930s, known for her emotionally nuanced performances in Hollywood’s Golden Age.
  • 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_69d8b907d05c819083cc3bd6021089e6 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4d9f81ff08190b7465e3c5568aa59 completed April 19, 2026, 1:34 p.m.
Created at: April 10, 2026, 10:27 a.m.