Triple

T9816142
Position Surface form Disambiguated ID Type / Status
Subject Francis, Duke of Anjou E238408 entity
Predicate nobleTitle P914 FINISHED
Object Duke of Berry E424158 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: Duke of Berry | Statement: [Francis, Duke of Anjou, nobleTitle, Duke of Berry]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Duke of Berry
Context triple: [Francis, Duke of Anjou, nobleTitle, Duke of Berry]
  • A. Charles, Duke of Berry
    Charles, Duke of Berry was a French prince of the Bourbon dynasty, grandson of King Louis XIV, whose early death curtailed any significant political role.
  • B. Duke of Chartres
    The Duke of Chartres was a French noble title traditionally held by junior members of the royal House of Orléans.
  • C. Duke of Nevers
    The Duke of Nevers was a prominent French noble title historically associated with influential aristocratic families, including the House of Mazarin.
  • D. Duke of Saint-Fargeau
    The Duke of Saint-Fargeau was a French noble title held by Philippe de France, the younger brother of King Louis XIV.
  • E. Francis, Duke of Berry chosen
    Francis, Duke of Berry was a French prince of the late 15th century, notable as the younger son of King Charles VIII of France and Anne of Brittany.
  • 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_69ca84dfde1481909f47c286d715f892 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cdb2f341648190bf8343e1124085cb completed April 2, 2026, 12:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69d2b5aab5408190aacdc310222bb85b completed April 5, 2026, 7:19 p.m.
Created at: March 30, 2026, 8:30 p.m.