Triple

T22094044
Position Surface form Disambiguated ID Type / Status
Subject My Life as a Dog E545978 entity
Predicate starring P1507 FINISHED
Object Anki Lidén 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: Anki Lidén | Statement: [My Life as a Dog, starring, Anki Lidén]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Anki Lidén
Context triple: [My Life as a Dog, starring, Anki Lidén]
  • A. Anki Lidén chosen
    Anki Lidén is a Swedish actress known for her extensive work in film, television, and theater, and as the mother of the late DJ and producer Avicii.
  • B. Ylva Johansson
    Ylva Johansson is a Swedish politician who has served as European Commissioner for Home Affairs and previously held several ministerial posts in the Swedish government.
  • C. Lina Leandersson
    Lina Leandersson is a Swedish actress best known for her acclaimed performance as the child vampire Eli in the 2008 horror film "Let the Right One In."
  • D. Mina Sundwall
    Mina Sundwall is an American actress best known for playing Penny Robinson in the Netflix science fiction series "Lost in Space."
  • E. Emma Andersson
    Emma Andersson is known as the spouse of Swedish ice hockey star Henrik Zetterberg.
  • 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_69e11e36d03c8190a83a1ba802b7231b completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f128e766388190aad1039fe0849771 completed April 28, 2026, 9:38 p.m.
Created at: April 16, 2026, 8:29 p.m.