Triple

T21200385
Position Surface form Disambiguated ID Type / Status
Subject Halfdan Ragnarsson E522438 entity
Predicate ethnicity P194 FINISHED
Object Norse 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: Norse | Statement: [Halfdan Ragnarsson, ethnicity, Norse]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Norse
Context triple: [Halfdan Ragnarsson, ethnicity, Norse]
  • A. Norse chosen
    Norse is a historical North Germanic language group, including Old Norse, that was spoken by the Vikings and significantly influenced many modern Scandinavian and North Atlantic languages.
  • B. Norse
    Norse is the nickname and athletic identity used by Northern Kentucky University's sports teams.
  • C. Norwegian Norse
    Norwegian Norse were medieval Scandinavian settlers from Norway who expanded across the North Atlantic, establishing communities in places such as Iceland and Greenland.
  • D. NORSE
    NORSE is the stock ticker symbol for Norse Atlantic Airways, a low-cost long-haul airline based in Norway.
  • E. Old Norse language
    Old Norse was the North Germanic language spoken by the inhabitants of Scandinavia and their overseas settlements during the Viking Age and is the ancestor of modern Scandinavian languages like Icelandic and Norwegian.
  • 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_69e0b5112d8881909510b2dcdc93106d completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e73430c5a08190aeb6a62eec0f43a3 completed April 21, 2026, 8:24 a.m.
Created at: April 16, 2026, 3:18 p.m.