Triple

T19154670
Position Surface form Disambiguated ID Type / Status
Subject Vals-près-le-Puy E468900 entity
Predicate demonym P191 FINISHED
Object Valois 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: Valois | Statement: [Vals-près-le-Puy, demonym, Valois]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Valois
Context triple: [Vals-près-le-Puy, demonym, Valois]
  • A. Valois chosen
    Valois was a prominent French royal dynasty that ruled France during the late Middle Ages and Renaissance, succeeding the Capetians and preceding the Bourbons.
  • B. Ansouis
    Ansouis is a picturesque hilltop village in southeastern France, renowned for its medieval château and traditional Provençal character.
  • C. Capet
    Capet is the dynastic surname of the medieval French royal house that began with Hugh Capet and ruled France for centuries.
  • D. Dauphine of France
    The Dauphine of France was the title given to the wife of the heir apparent to the French throne, signifying her status as the kingdom’s future queen consort.
  • E. Souveraine of Valois
    Souveraine of Valois was a French noblewoman of the Valois dynasty, known primarily as the daughter of Charles, Count of Angoulême.
  • 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_69d8dd084ff48190ac0f8c46ee722629 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5eeb81bf08190b0352137eb4a5763 completed April 20, 2026, 9:15 a.m.
Created at: April 10, 2026, 12:06 p.m.