Triple

T20874865
Position Surface form Disambiguated ID Type / Status
Subject Selma Lagerlöf E513990 entity
Predicate notableWork P4 FINISHED
Object Körkarlen 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: Körkarlen | Statement: [Selma Lagerlöf, notableWork, Körkarlen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Körkarlen
Context triple: [Selma Lagerlöf, notableWork, Körkarlen]
  • A. Körkarlen chosen
    Körkarlen is a 1912 novel by Swedish author Selma Lagerlöf that blends supernatural elements with moral and social themes, famously inspiring Victor Sjöström’s classic 1921 silent film adaptation "The Phantom Carriage."
  • B. Koka björn
    Koka björn is a novel by Swedish author Mikael Niemi, known for its darkly humorous and suspenseful portrayal of life in the far north of Sweden.
  • C. Damkronorna
    Damkronorna is the Swedish national women's ice hockey team that represents Sweden in international women's ice hockey competitions.
  • D. Hestmannen
    Hestmannen is a distinctive, steep-sided mountain and notable landmark rising from an island along Norway’s Helgeland coast.
  • E. Kultorvet
    Kultorvet is a historic public square and marketplace in central Copenhagen, Denmark, known for its shops, cafés, and pedestrian-friendly urban space.
  • 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_69e0b4f675cc8190b4e745225b62eb66 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c674075081909e0819b20bdbb7f4 completed April 21, 2026, 12:36 a.m.
Created at: April 16, 2026, 12:45 p.m.