Triple

T7913394
Position Surface form Disambiguated ID Type / Status
Subject Frank Costello E183754 entity
Predicate spouse P13 FINISHED
Object Lauretta Geigerman E183754 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: Lauretta Geigerman | Statement: [Frank Costello, spouse, Lauretta Geigerman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lauretta Geigerman
Context triple: [Frank Costello, spouse, Lauretta Geigerman]
  • A. Lauretta Geigerman chosen
    Lauretta Geigerman was the wife of American mob boss Frank Costello, a prominent figure in mid-20th-century organized crime.
  • B. Eleanor Geisman
    Eleanor Geisman, better known by her stage name June Allyson, was a popular American film and television actress renowned for her girl-next-door charm in 1940s and 1950s Hollywood.
  • C. Rita Gilman
    Rita Gilman was the wife of American film actor Wallace Beery, known primarily for her marriage to the prominent Hollywood star.
  • D. Marion Rothman
    Marion Rothman was an American film editor known for her work on notable films of the 1960s and 1970s, including the crime thriller "The Boston Strangler."
  • E. Daphne Kluger
    Daphne Kluger is a glamorous, high-profile actress and the unsuspecting target of the jewel heist in the film "Ocean's 8."
  • 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_69ca828dec0c81908b8f55a4dbbb53ff completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb3a748f4c8190bcd868de2fcf0b3a completed March 31, 2026, 3:07 a.m.
NED1 Entity disambiguation (via context triple) batch_69ccec781ac88190b52305beaa213415 completed April 1, 2026, 9:59 a.m.
Created at: March 30, 2026, 5:04 p.m.