Triple

T9023162
Position Surface form Disambiguated ID Type / Status
Subject Vikes E215976 entity
Predicate mascot P52 FINISHED
Object Viktor the Viking E215968 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: Viktor the Viking | Statement: [Vikes, mascot, Viktor the Viking]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Viktor the Viking
Context triple: [Vikes, mascot, Viktor the Viking]
  • A. Viktor the Viking chosen
    Viktor the Viking is the costumed, Nordic-themed mascot who represents the NFL’s Minnesota Vikings at games and team events.
  • B. Magnus the Viking
    Magnus the Viking is the costumed Viking mascot representing Cleveland State University's athletic teams and school spirit.
  • C. Eric the Viking
    Eric the Viking is a 1989 British-Norwegian fantasy comedy film directed by Monty Python member Terry Jones, loosely based on his children’s book "The Saga of Erik the Viking."
  • D. Ivar
    Ivar is a masculine given name of Old Norse origin, traditionally used in Scandinavian countries.
  • E. Ragnar Lodbrok
    Ragnar Lodbrok is a legendary Viking hero and king of Scandinavian sagas, famed for his raids on England and France and his dramatic, mythologized death.
  • 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_69ca83a5fa88819088144801b4dd7245 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc6a7a770081908dfe3ce3374a04ba completed April 1, 2026, 12:44 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfdbbcaedc819084f8b057fbfcb0e7 completed April 3, 2026, 3:24 p.m.
Created at: March 30, 2026, 7:07 p.m.