Triple

T16857978
Position Surface form Disambiguated ID Type / Status
Subject Stig Björkman E409836 entity
Predicate name P16 FINISHED
Object Stig Björkman E409836 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: Stig Björkman | Statement: [Stig Björkman, name, Stig Björkman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Stig Björkman
Context triple: [Stig Björkman, name, Stig Björkman]
  • A. Stig Björkman chosen
    Stig Björkman is a Swedish film critic, director, and writer known for his documentaries and in-depth interviews with prominent filmmakers and actors.
  • B. Björn Waldegård
    Björn Waldegård was a Swedish rally driver and the inaugural World Rally Championship drivers’ title winner, renowned for his success with multiple manufacturers during the 1970s and 1980s.
  • C. Patrik Stymne
    Patrik Stymne is a Swedish entrepreneur best known as a co-founder of the mobile gaming company King Digital Entertainment, creator of Candy Crush Saga.
  • D. Torbjörn Edström
    Torbjörn Edström is a notable individual recognized for bearing the Swedish surname Edström.
  • E. Lars Ljungqvist
    Lars Ljungqvist is an economist known for his influential work in macroeconomics and labor economics, including co-authoring the widely used graduate textbook "Recursive Macroeconomic Theory" with Thomas J. Sargent.
  • 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_69d88395e6c88190b22730f335107c14 completed April 10, 2026, 4:59 a.m.
NER Named-entity recognition batch_69e3b37ef4748190b149d98fc0ab4205 completed April 18, 2026, 4:38 p.m.
NED1 Entity disambiguation (via context triple) batch_6a01232992ec81909dbbd2e28111e8f4 completed May 11, 2026, 12:30 a.m.
Created at: April 10, 2026, 5:24 a.m.