Triple

T22756425
Position Surface form Disambiguated ID Type / Status
Subject John of Denmark E562855 entity
Predicate fullName P16 FINISHED
Object John of Denmark 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: John of Denmark | Statement: [John of Denmark, fullName, John of Denmark]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John of Denmark
Context triple: [John of Denmark, fullName, John of Denmark]
  • A. John of Denmark chosen
    John of Denmark was a 16th-century Danish prince, the son of King Christian II of Denmark and Isabella of Austria, who died in childhood.
  • B. John of Denmark
    John of Denmark was a Danish prince of the House of Oldenburg, known primarily as the son of King Frederick II and heir apparent who died before ascending the throne.
  • C. Christopher of Denmark
    Christopher of Denmark was a 13th-century Danish prince, son of Matilda of Holstein and King Abel of Denmark.
  • D. Hans of Denmark
    Hans of Denmark was a late 15th- and early 16th-century king who ruled Denmark, Norway, and briefly Sweden within the Kalmar Union.
  • E. Ulrik of Denmark
    Ulrik of Denmark was a Danish prince of the early 17th century, known as a younger son of King Christian IV who pursued a career in the military and nobility rather than ruling.
  • 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_69e24551ec7881909a9c924dbea155f6 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f179bd22588190ac724a656194f5b9 completed April 29, 2026, 3:23 a.m.
Created at: April 17, 2026, 3:25 p.m.