Triple

T7713483
Position Surface form Disambiguated ID Type / Status
Subject Pandora and the Flying Dutchman E174822 entity
Predicate starring P1507 FINISHED
Object Sheila Sim E155436 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: Sheila Sim | Statement: [Pandora and the Flying Dutchman, starring, Sheila Sim]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sheila Sim
Context triple: [Pandora and the Flying Dutchman, starring, Sheila Sim]
  • A. Sheila Sim chosen
    Sheila Sim was a British actress and model best known for her film and stage work in the mid-20th century and her long association with the British theatre and film community.
  • B. Anne Rennie
    Anne Rennie is known as the wife of bestselling adventure novelist Wilbur Smith.
  • C. Sheila Jordan
    Sheila Jordan is an American jazz singer renowned for her bebop-influenced vocal style, innovative scat singing, and expressive interpretations of standards.
  • D. Patricia Clarkson
    Patricia Clarkson is an American actress acclaimed for her versatile performances in film, television, and theater, often in complex supporting roles.
  • E. Joanne Dru
    Joanne Dru was an American film and television actress best known for her roles in classic Westerns and dramas of the 1940s and 1950s.
  • 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_69c6995c463c8190a14458036249d419 completed March 27, 2026, 2:51 p.m.
NER Named-entity recognition batch_69c702c96e388190898165f84d646c0e completed March 27, 2026, 10:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69c91f4fb010819080ced464e4a71658 completed March 29, 2026, 12:47 p.m.
Created at: March 27, 2026, 4:04 p.m.