Triple

T12841104
Position Surface form Disambiguated ID Type / Status
Subject Rudolph Giuliani E307052 entity
Predicate spouse P13 FINISHED
Object Regina Peruggi E322930 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: Regina Peruggi | Statement: [Rudolph Giuliani, spouse, Regina Peruggi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Regina Peruggi
Context triple: [Rudolph Giuliani, spouse, Regina Peruggi]
  • A. Regina Peruggi chosen
    Regina Peruggi is an American educator and academic administrator who has served as president of Kingsborough Community College in New York City.
  • B. Lisa Vultaggio
    Lisa Vultaggio is a Canadian actress best known for her role as Hannah Scott on the soap opera "General Hospital."
  • C. Kate Perugini
    Kate Perugini was a British painter and the daughter of novelist Charles Dickens, known for her portrait work and connections within Victorian artistic circles.
  • D. Alicia Cazzaniga
    Alicia Cazzaniga is an Argentine architect best known for co-designing the iconic modernist building of the National Library of Argentina in Buenos Aires.
  • E. Cristina Ferrare
    Cristina Ferrare is an American former fashion model, television talk-show host, and author known for her work in entertainment and lifestyle programming.
  • 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_69d7bdf52b94819096d6f0ba4ab50a98 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d96ff2ab60819085561a3120189985 completed April 10, 2026, 9:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69f7396b901c81908bfac5b40e3caed4 completed May 3, 2026, 12:02 p.m.
Created at: April 9, 2026, 5:35 p.m.