Triple

T4272604
Position Surface form Disambiguated ID Type / Status
Subject Love Me Tonight E96973 entity
Predicate starring P1507 FINISHED
Object Myrna Loy E173404 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: Myrna Loy | Statement: [Love Me Tonight, starring, Myrna Loy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Myrna Loy
Context triple: [Love Me Tonight, starring, Myrna Loy]
  • A. Myrna Loy chosen
    Myrna Loy was a popular American film actress of Hollywood’s Golden Age, best known for her sophisticated, witty roles in classics such as The Thin Man series.
  • B. Irene Dunne
    Irene Dunne was an American actress and singer celebrated for her work in both dramatic and screwball comedy films during Hollywood’s Golden Age.
  • C. Margaret Sullavan
    Margaret Sullavan was an acclaimed American stage and film actress of the 1930s and 1940s, best known for her sensitive, naturalistic performances in films such as "The Shop Around the Corner."
  • D. Joan Blondell
    Joan Blondell was a popular American film and stage actress of the 1930s and 1940s, known for her wisecracking, warm-hearted characters in numerous Warner Bros. productions.
  • E. Rosalind Russell
    Rosalind Russell was an acclaimed American actress best known for her sharp-witted performances in screwball comedies and strong, independent female roles on stage and screen.
  • 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_69b34543f06c8190915ebb1a4574ffa9 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b34ffe44508190875d734eb18dfb87 completed March 12, 2026, 11:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69be921df91881909c257fbd3c46073c completed March 21, 2026, 12:42 p.m.
Created at: March 12, 2026, 11:07 p.m.