Triple

T17602541
Position Surface form Disambiguated ID Type / Status
Subject Soubise E428738 entity
Predicate relatedTitle P914 FINISHED
Object Duke of Rohan 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: Duke of Rohan | Statement: [Soubise, relatedTitle, Duke of Rohan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Duke of Rohan
Context triple: [Soubise, relatedTitle, Duke of Rohan]
  • A. Duke of Rohan-Rohan
    The Duke of Rohan-Rohan was a French noble title held by a cadet branch of the powerful Rohan family, prominent at the royal court under the Ancien Régime.
  • B. Duke of Nevers
    The Duke of Nevers was a prominent French noble title historically associated with influential aristocratic families, including the House of Mazarin.
  • C. Duke of Montbazon chosen
    The Duke of Montbazon was a prominent French noble title historically associated with the influential Breton aristocratic House of Rohan.
  • D. Duke of Armagnac
    The Duke of Armagnac was a French noble title historically associated with high-ranking aristocrats and royal favorites, notably within the powerful House of Lorraine.
  • E. Duke of Auvergne
    The Duke of Auvergne was a high-ranking French noble title historically associated with the governance and lordship of the Auvergne region in central France.
  • 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_69d889e1c6148190ba76241e74688f8b completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e46c49dbe081909bd39879c70fe27c completed April 19, 2026, 5:46 a.m.
Created at: April 10, 2026, 5:51 a.m.