Triple

T9939958
Position Surface form Disambiguated ID Type / Status
Subject Haakon Magnus E194052 entity
Predicate name P16 FINISHED
Object Haakon Magnus E194052 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: Haakon Magnus | Statement: [Haakon Magnus, name, Haakon Magnus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Haakon Magnus
Context triple: [Haakon Magnus, name, Haakon Magnus]
  • A. Haakon Magnus chosen
    Haakon Magnus is the Crown Prince of Norway and heir apparent to the Norwegian throne.
  • B. Haakon V
    Haakon V was a medieval King of Norway, notable as the last ruler of the House of Sverre and for moving the Norwegian capital to Oslo.
  • C. Haakon II of Norway
    Haakon II of Norway was a 12th-century Norwegian king whose brief and turbulent reign was marked by civil war and conflict over the royal succession.
  • D. Haakon the Young
    Haakon the Young was a 13th-century Norwegian prince and co-king, known as the eldest surviving son and designated heir of King Haakon IV of Norway.
  • E. Haakon III of Norway
    Haakon III of Norway was a medieval Norwegian king whose brief reign was marked by dynastic conflict during the turbulent civil war era.
  • 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_69ca82e409348190a393777356b80a2a completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cdb5e819e08190967b799fd236749e completed April 2, 2026, 12:18 a.m.
NED1 Entity disambiguation (via context triple) batch_69d228fdb8e48190808702d48470395a completed April 5, 2026, 9:18 a.m.
Created at: March 30, 2026, 8:44 p.m.