Triple

T18706641
Position Surface form Disambiguated ID Type / Status
Subject François Clary E457386 entity
Predicate relative P37 FINISHED
Object Joseph Bonaparte 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: Joseph Bonaparte | Statement: [François Clary, relative, Joseph Bonaparte]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Joseph Bonaparte
Context triple: [François Clary, relative, Joseph Bonaparte]
  • A. Joseph Bonaparte chosen
    Joseph Bonaparte was the elder brother of Napoleon who became King of Naples and later King of Spain during the Napoleonic era.
  • B. Jérôme Bonaparte
    Jérôme Bonaparte was the youngest brother of Napoleon who became King of Westphalia and later served as a Marshal of France.
  • C. Louis Bonaparte
    Louis Bonaparte was a younger brother of Napoleon who became King of Holland and played a notable role in European politics during the Napoleonic era.
  • D. Joseph Lucien Bonaparte
    Joseph Lucien Bonaparte was a member of the Bonaparte family and the son of the noted French ornithologist and politician Charles Lucien Bonaparte.
  • E. Napoléon Jérôme Bonaparte
    Napoléon Jérôme Bonaparte was a 19th-century French prince of the Bonaparte family who pursued a military and political career under the Second French Empire.
  • 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_69d8d392aad081909fe31aa03e6e97d1 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e5671717b88190974f542015f641e8 completed April 19, 2026, 11:36 p.m.
Created at: April 10, 2026, 11:50 a.m.