Triple

T3465232
Position Surface form Disambiguated ID Type / Status
Subject Lorenzo de' Medici E73120 entity
Predicate spouse P13 FINISHED
Object Clarice Orsini E73494 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: Clarice Orsini | Statement: [Lorenzo de' Medici, spouse, Clarice Orsini]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Clarice Orsini
Context triple: [Lorenzo de' Medici, spouse, Clarice Orsini]
  • A. Clarice Orsini chosen
    Clarice Orsini was a 15th-century Italian noblewoman of the Orsini family and wife of Lorenzo de' Medici, noted as the mother of Pope Leo X.
  • B. Josephine Nitti
    Josephine Nitti was the wife of notorious Chicago Outfit mob boss Frank Nitti, connecting her to the inner circle of American organized crime during the Prohibition era.
  • C. Catherine Poletti
    Catherine Poletti is a French sports organizer best known for co-founding and directing the Ultra-Trail du Mont-Blanc, one of the world’s most prestigious trail running events.
  • D. Marguerite De La Motte
    Marguerite De La Motte was an American silent film actress best known for her leading roles in early 1920s adventure and drama films.
  • E. Beatrice Warren
    Beatrice Warren was a physicist whose contributions to the field of diffraction physics were significant enough to have a prestigious scientific award named in her honor.
  • 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_69ad85b224d481908ff8be51338d24ff completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adbb0f2d3881908a5fa871341564ed completed March 8, 2026, 6:08 p.m.
NED1 Entity disambiguation (via context triple) batch_69b3680412c0819086da51a05b24a676 completed March 13, 2026, 1:27 a.m.
Created at: March 8, 2026, 3:17 p.m.