Triple

T8871846
Position Surface form Disambiguated ID Type / Status
Subject Paulette Goddard E211174 entity
Predicate birthName P65 FINISHED
Object Marion Levy E211174 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: Marion Levy | Statement: [Paulette Goddard, birthName, Marion Levy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marion Levy
Context triple: [Paulette Goddard, birthName, Marion Levy]
  • A. Marion Levy chosen
    Marion Levy, better known by her stage name Paulette Goddard, was an American actress and film star prominent in the 1930s and 1940s, noted for her roles in Charlie Chaplin films and several Hollywood classics.
  • B. Marjorie Fried
    Marjorie Fried was the wife of Nobel Prize–winning geneticist George W. Beadle.
  • C. Lillian Lehman
    Lillian Lehman is an American actress known for her extensive work in television dramas and soap operas, including roles on shows like "Hill Street Blues" and "Sunset Beach."
  • D. Lucile E. Greene
    Lucile E. Greene was an American writer and activist known for her work in civil rights and social justice.
  • E. Marion Weiss
    Marion Weiss is an American architect and co-founder of the firm Weiss/Manfredi, known for her innovative, landscape-integrated public and cultural 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_69ca838e78748190934d82db3104f855 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc61281e888190a32b08980310979f completed April 1, 2026, 12:04 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfba149400819096cb93fdda440dcd completed April 3, 2026, 1:01 p.m.
Created at: March 30, 2026, 6:51 p.m.