Triple

T12859810
Position Surface form Disambiguated ID Type / Status
Subject Lisbeth Salander E307553 entity
Predicate seeksRevengeOn P20070 FINISHED
Object Nils Bjurman E1015725 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: Nils Bjurman | Statement: [Lisbeth Salander, seeksRevengeOn, Nils Bjurman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nils Bjurman
Context triple: [Lisbeth Salander, seeksRevengeOn, Nils Bjurman]
  • A. Nils Bjurman chosen
    Nils Bjurman is a corrupt and sadistic legal guardian in Stieg Larsson’s Millennium series, known for exploiting and tormenting Lisbeth Salander.
  • B. Nils Sjöberg
    Nils Sjöberg is a pseudonym used by Taylor Swift for her work as a songwriter and producer, notably on the hit song "This Is What You Came For."
  • C. Erik Kråkström
    Erik Kråkström was a Finnish architect known for his modernist industrial and residential designs, including significant work on the Sunila Pulp Mill complex.
  • D. 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.
  • E. Leif Sjöberg
    Leif Sjöberg was a Swedish translator and scholar known for bringing modern Arabic literature to Scandinavian readers.
  • 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_69d7bdf5e7cc8190be357278bc5ba3bb completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d970242bd48190941cbae0315ebc3d completed April 10, 2026, 9:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6cbb93c688190910ffb6bc6fbef3f completed May 3, 2026, 4:14 a.m.
Created at: April 9, 2026, 5:37 p.m.