Triple

T9205360
Position Surface form Disambiguated ID Type / Status
Subject Michael Cohen E220961 entity
Predicate spouse P13 FINISHED
Object Laura Shusterman E220961 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: Laura Shusterman | Statement: [Michael Cohen, spouse, Laura Shusterman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Laura Shusterman
Context triple: [Michael Cohen, spouse, Laura Shusterman]
  • A. Laura Shusterman chosen
    Laura Shusterman is the wife of former Donald Trump attorney Michael Cohen and a Ukrainian-born businesswoman who has been linked to some of his real estate and taxi-medallion ventures.
  • B. Rachel Leibowitz
    Rachel Leibowitz is a person notable enough to be specifically cited as a bearer of the surname Leibowitz.
  • C. Ellen Mirojnick
    Ellen Mirojnick is an American costume designer known for her influential work on films such as "Basic Instinct" and numerous other high-profile productions.
  • D. Rachel Buchman
    Rachel Buchman is the titular bride and central figure in the 2008 drama film "Rachel Getting Married," around whose wedding and family tensions the story revolves.
  • E. Deborah Liebling
    Deborah Liebling is an American television and film producer and executive known for her work on comedy projects.
  • 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_69ca83e8e9248190862cf3e41693b310 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69ccd947a0a08190966f22a6207c9120 completed April 1, 2026, 8:37 a.m.
NED1 Entity disambiguation (via context triple) batch_69d19f50f1c4819099a9c511f58e9873 completed April 4, 2026, 11:31 p.m.
Created at: March 30, 2026, 7:26 p.m.