Triple

T5989951
Position Surface form Disambiguated ID Type / Status
Subject Bruno Mussolini E133320 entity
Predicate spouse P13 FINISHED
Object Gina Ruberti E133320 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: Gina Ruberti | Statement: [Bruno Mussolini, spouse, Gina Ruberti]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gina Ruberti
Context triple: [Bruno Mussolini, spouse, Gina Ruberti]
  • A. Gina Ruberti chosen
    Gina Ruberti was the wife of Bruno Mussolini, the son of Italian dictator Benito Mussolini.
  • B. Roberta Romano
    Roberta Romano is a prominent American legal scholar known for her influential work on corporate law and governance, and for serving as a long-time professor at Yale Law School.
  • C. Nadine Caridi
    Nadine Caridi is a British-born former model and licensed marriage and family therapist best known as the ex-wife of stockbroker Jordan Belfort, whose life inspired the film "The Wolf of Wall Street."
  • D. Melissa Agretti
    Melissa Agretti is a central, scheming heiress character from the 1980s American prime-time soap opera "Falcon Crest."
  • E. Christine Toretti
    Christine Toretti is an American businesswoman and political donor known for her leadership in the energy industry and involvement in Republican Party politics.
  • 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_69c0087010d081908bb8142342d63330 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c04dc76fd481908cc3f327e532a1a6 completed March 22, 2026, 8:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69c62cf2edd48190b3d5f6bf27075fed completed March 27, 2026, 7:08 a.m.
Created at: March 22, 2026, 4:05 p.m.