Triple

T4084549
Position Surface form Disambiguated ID Type / Status
Subject Danny DeVito E87557 entity
Predicate spouse P13 FINISHED
Object Rhea Perlman E336839 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: Rhea Perlman | Statement: [Danny DeVito, spouse, Rhea Perlman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rhea Perlman
Context triple: [Danny DeVito, spouse, Rhea Perlman]
  • A. Rhea Perlman chosen
    Rhea Perlman is an American actress best known for her Emmy-winning role as the sharp-tongued waitress Carla Tortelli on the classic sitcom "Cheers."
  • B. Jessica Walter
    Jessica Walter was an American actress best known for her sharp, comedic portrayal of Lucille Bluth on the television series "Arrested Development."
  • C. Candice Bergen
    Candice Bergen is an American actress and former fashion model best known for her Emmy-winning role as the sharp-tongued journalist Murphy Brown on the hit television sitcom of the same name.
  • D. Dianne Wiest
    Dianne Wiest is an acclaimed American actress known for her versatile performances in film, television, and theater, including multiple award-winning supporting roles.
  • E. Anne McDonnell
    Anne McDonnell was an American socialite best known as the first wife of industrialist Henry Ford II.
  • 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_69aed9435cf48190ad1da737c962d19d completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefc7a4b488190ab466e2c50329ab3 completed March 9, 2026, 4:59 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5a83aaabc81908a204008ebe292b2 completed March 14, 2026, 6:26 p.m.
Created at: March 9, 2026, 3:39 p.m.