Triple

T11728160
Position Surface form Disambiguated ID Type / Status
Subject Karlssen E278828 entity
Predicate hasSpellingVariant P457 FINISHED
Object Karlsen E943417 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: Karlsen | Statement: [Karlssen, hasSpellingVariant, Karlsen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Karlsen
Context triple: [Karlssen, hasSpellingVariant, Karlsen]
  • A. Karlsen chosen
    Karlsen is a Scandinavian patronymic surname, particularly common in Norway and Denmark, meaning "son of Karl."
  • B. Karlssen
    Karlssen is a Scandinavian-origin surname, likely a patronymic variant related to the more common name Carlson.
  • C. Haraldsen
    Haraldsen is a Norwegian surname most notably borne by Queen Sonja of Norway before her marriage into the royal family.
  • D. Lársen
    Lársen is a variant spelling of the surname Larsen, a common Scandinavian family name typically meaning "son of Lars."
  • E. Torbjørn
    Torbjørn is a Scandinavian masculine given name, particularly common in Norway, derived from Old Norse elements meaning "Thor" and "bear."
  • 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_69d6aaffec6881908bead509e8621742 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a4d80ef881908cab956787ab07fd completed April 10, 2026, 7:20 a.m.
NED1 Entity disambiguation (via context triple) batch_69f1306859208190bc5d0b4f81fb1bff completed April 28, 2026, 10:10 p.m.
Created at: April 8, 2026, 9:41 p.m.