Triple

T38433830
Position Surface form Disambiguated ID Type / Status
Subject Maria Beatrice d’Este E903879 entity
Predicate successorAsDuchessOfMassa P203047 FINISHED
Object Francis IV, Duke of Modena 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: Francis IV, Duke of Modena | Statement: [Maria Beatrice d’Este, successorAsDuchessOfMassa, Francis IV, Duke of Modena]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: successorAsDuchessOfMassa
Context triple: [Maria Beatrice d’Este, successorAsDuchessOfMassa, Francis IV, Duke of Modena]
  • A. successorAsDuchessOfBrittany
    Indicates that one entity became the next Duchess of Brittany following another entity in that title or position.
  • B. successorAsDuchessConsort
    Indicates that one individual becomes the next duchess consort, directly following another in that role.
  • C. reignAsDuchessFrom
    Indicates that a person holds and exercises the title and authority of a duchess over a specified domain starting from a given point in time.
  • D. successorAsDuchessOfBedford
    Indicates that one person became the next holder of the title Duchess of Bedford after another person.
  • E. successorAsDukeOfSavoy
    Indicates that one entity became the next Duke of Savoy following another entity in the line of succession.
  • F. None of above. chosen

Provenance (4 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_69f76e6a2024819081aa04f4932f89d2 completed May 3, 2026, 3:48 p.m.
NER Named-entity recognition batch_6a01185c46f0819089b4a2ad3c3e2f33 completed May 10, 2026, 11:44 p.m.
PD Predicate disambiguation batch_6a0117e19e008190870663dd45084416 completed May 10, 2026, 11:42 p.m.
PDg Predicate description generation batch_6a01185b580c8190a01f65404486cfec completed May 10, 2026, 11:44 p.m.
Created at: May 3, 2026, 4:31 p.m.