Triple

T13753687
Position Surface form Disambiguated ID Type / Status
Subject Shirley Maisel E330419 entity
Predicate portrayedBy P1507 FINISHED
Object Caroline Aaron E365257 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: Caroline Aaron | Statement: [Shirley Maisel, portrayedBy, Caroline Aaron]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Caroline Aaron
Context triple: [Shirley Maisel, portrayedBy, Caroline Aaron]
  • A. Caroline Aaron chosen
    Caroline Aaron is an American actress known for her character roles in film, television, and theater, including frequent collaborations with director Woody Allen and a prominent part in the series "The Marvelous Mrs. Maisel."
  • B. Caroline Ross
    Caroline Ross is a film editor known for her work on the science fiction movie "Starship Troopers."
  • C. Caroline Rose Hunt
    Caroline Rose Hunt was an American heiress, hotelier, and philanthropist best known for founding the luxury Rosewood Hotels & Resorts.
  • D. Caroline Pitts
    Caroline Pitts was the wife of U.S. Supreme Court Justice Henry Billings Brown.
  • E. Caroline Smith
    Caroline Smith is known as the wife of American television executive and entrepreneur Julian Sinclair Smith.
  • 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_69d81c573f288190aa2403d484fa3d49 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de0215cfa08190aaed8b089aff217b completed April 14, 2026, 9 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7a85813e88190a63fecf8b0675df6 completed May 3, 2026, 7:56 p.m.
Created at: April 9, 2026, 10:09 p.m.