Triple

T11666793
Position Surface form Disambiguated ID Type / Status
Subject Room Service E277269 entity
Predicate stars P1956 FINISHED
Object Ann Miller E219998 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: Ann Miller | Statement: [Room Service, stars, Ann Miller]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ann Miller
Context triple: [Room Service, stars, Ann Miller]
  • A. Ann Miller chosen
    Ann Miller was an American actress, singer, and acclaimed tap dancer known for her energetic performances in classic Hollywood musicals of the 1940s and 1950s.
  • B. Martha Raye
    Martha Raye was an American comic actress and singer known for her brash, big-mouthed persona in film and television and for her extensive USO performances entertaining troops during multiple wars.
  • C. Marilyn Miller
    Marilyn Miller was a celebrated American Broadway musical star of the 1910s and 1920s, renowned for her charismatic dancing, singing, and stage presence.
  • D. Mitzi Gaynor
    Mitzi Gaynor is an American actress, singer, and dancer best known for her starring role in the film musical "South Pacific" and her vibrant performances on stage and television.
  • E. Dinah Shore
    Dinah Shore was a popular American singer, actress, and television personality best known for her hit recordings and pioneering work in early television variety shows.
  • 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_69d6aafd0a448190b44da30af8c6c519 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a43f438081909da476294a057c38 completed April 10, 2026, 7:18 a.m.
NED1 Entity disambiguation (via context triple) batch_69f48a027dec8190aea103f0974186b0 completed May 1, 2026, 11:09 a.m.
Created at: April 8, 2026, 9:39 p.m.