Triple

T10230332
Position Surface form Disambiguated ID Type / Status
Subject Eva Åkesson E243322 entity
Predicate familyName P18 FINISHED
Object Åkesson E795950 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: Åkesson | Statement: [Eva Åkesson, familyName, Åkesson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Åkesson
Context triple: [Eva Åkesson, familyName, Åkesson]
  • A. Åkesson chosen
    Åkesson is a Swedish surname most prominently associated with Jimmie Åkesson, the long-time leader of the Sweden Democrats political party.
  • B. Åkerman
    Åkerman is a Swedish surname most notably borne by Canadian-Swedish actress and model Malin Åkerman.
  • C. Lukasson
    Lukasson is a surname of likely Scandinavian origin, commonly used as a patronymic family name.
  • D. Danielsson
    Danielsson is a Swedish surname commonly borne by individuals of Scandinavian origin.
  • E. Olof Grind
    Olof Grind is a Swedish photographer and visual artist known for his atmospheric, cinematic imagery used in music-related artwork and editorial projects.
  • 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_69d381b0f97c819085c9b45799a5fb7c completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4d20a25dc8190bd448f7ba7a13cbd completed April 7, 2026, 9:44 a.m.
NED1 Entity disambiguation (via context triple) batch_69d6f73610fc8190965c4e45a9deeac6 completed April 9, 2026, 12:47 a.m.
Created at: April 6, 2026, 11:19 a.m.