Triple

T13003643
Position Surface form Disambiguated ID Type / Status
Subject Stieg Larsson E322231 entity
Predicate name P16 FINISHED
Object Stieg Larsson E322231 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: Stieg Larsson | Statement: [Stieg Larsson, name, Stieg Larsson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Stieg Larsson
Context triple: [Stieg Larsson, name, Stieg Larsson]
  • A. Stieg Larsson chosen
    Stieg Larsson was a Swedish journalist and crime novelist best known for his posthumously published Millennium series, beginning with "The Girl with the Dragon Tattoo."
  • B. Henning Mankell
    Henning Mankell was a Swedish author and playwright best known internationally for his crime novels featuring detective Kurt Wallander.
  • C. Jo Nesbø
    Jo Nesbø is a Norwegian crime fiction author and musician best known for his Harry Hole detective series and internationally bestselling thrillers.
  • D. John Ajvide Lindqvist
    John Ajvide Lindqvist is a Swedish author and screenwriter best known for his modern horror novels that blend supernatural elements with stark social realism.
  • E. Sune Lindqvist
    Sune Lindqvist was a Swedish archaeologist and scholar known for his influential excavations and research on early Scandinavian burial sites and Iron Age history.
  • 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_69d807657e8c8190bd9435ee2f823845 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69d97e9a2a448190968833354280e474 completed April 10, 2026, 10:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6cbc5c9a88190b70bda472bf3b062 completed May 3, 2026, 4:15 a.m.
Created at: April 9, 2026, 8:47 p.m.