Triple

T6134333
Position Surface form Disambiguated ID Type / Status
Subject Lester Anthony Minnelli E136795 entity
Predicate spouse P13 FINISHED
Object Georgette Magnani E186298 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: Georgette Magnani | Statement: [Lester Anthony Minnelli, spouse, Georgette Magnani]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Georgette Magnani
Context triple: [Lester Anthony Minnelli, spouse, Georgette Magnani]
  • A. Georgette Magnani chosen
    Georgette Magnani was the first wife of acclaimed American film director Vincente Minnelli, known primarily for her brief marriage to him before his rise to major Hollywood fame.
  • B. Marie Mosquini
    Marie Mosquini was an American silent film actress best known for her work in Hal Roach comedies during the 1910s and 1920s.
  • C. Lauretta Geigerman
    Lauretta Geigerman was the wife of American mob boss Frank Costello, a prominent figure in mid-20th-century organized crime.
  • D. Carmen Lasky
    Carmen Lasky is an Australian former violinist best known as the first wife of renowned conductor Zubin Mehta.
  • E. Margaret Mazzantini
    Margaret Mazzantini is an Italian novelist, playwright, and actress best known internationally for her award-winning novels such as "Don't Move."
  • 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_69c008a179388190a3b5a081bbf46d55 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c05c7f34d081909e589b201b22be21 completed March 22, 2026, 9:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69c1416e8fa8819092bf830cbaa56647 completed March 23, 2026, 1:34 p.m.
Created at: March 22, 2026, 4:15 p.m.