Triple

T5683443
Position Surface form Disambiguated ID Type / Status
Subject Lee Radziwill E125251 entity
Predicate parent P120 FINISHED
Object Janet Norton Lee E168779 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: Janet Norton Lee | Statement: [Lee Radziwill, parent, Janet Norton Lee]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Janet Norton Lee
Context triple: [Lee Radziwill, parent, Janet Norton Lee]
  • A. Janet Norton Lee chosen
    Janet Norton Lee was an American socialite and philanthropist best known as the mother of First Lady Jacqueline Kennedy Onassis.
  • B. Edna L. Lee
    Edna L. Lee was an American novelist best known for writing the book that inspired the classic 1955 melodrama film "All That Heaven Allows."
  • C. Janet Patterson
    Janet Patterson was an acclaimed Australian costume and production designer known for her richly detailed period work on films such as "The Piano" and "Oscar and Lucinda."
  • D. Sherri Parker Lee
    Sherri Parker Lee is a benefactor and namesake associated with the University of Tennessee’s softball program, honored through the naming of Sherri Parker Lee Stadium.
  • E. Florence Lee
    Florence Lee was an early 20th-century film actress best known for her supporting roles in silent comedies, including work with Charlie Chaplin.
  • 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_69c0082a884c8190a79001bae658941f completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c023b780248190a912d2dddbd0aa17 completed March 22, 2026, 5:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69c107bf6994819089e1211ffe343094 completed March 23, 2026, 9:28 a.m.
Created at: March 22, 2026, 3:44 p.m.