Triple

T20246220
Position Surface form Disambiguated ID Type / Status
Subject Pure Country E498430 entity
Predicate starring P1507 FINISHED
Object Isabel Glasser NE NERFINISHED

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: Isabel Glasser | Statement: [Pure Country, starring, Isabel Glasser]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Isabel Glasser
Context triple: [Pure Country, starring, Isabel Glasser]
  • A. Isabel Glasser chosen
    Isabel Glasser is an American actress best known for her roles in films like "Forever Young" and "Pure Country" as well as various television appearances.
  • B. Emmeline Obermeyer
    Emmeline Obermeyer was the first wife of influential American photographer and modern art promoter Alfred Stieglitz.
  • C. Frances Seymour
    Frances Seymour was an English noblewoman and literary patron who became a prominent figure at the Stuart court and later served as a lady of the bedchamber to Queen Caroline.
  • D. Harriet Heyman
    Harriet Heyman is an American writer and former journalist known for her work in fiction and nonfiction, as well as her marriage to venture capitalist Michael Moritz.
  • E. Harriet Heyman
    Harriet Heyman is an American writer and philanthropist best known as the co-founder of the Crankstart foundation, which supports education, arts, and social justice initiatives.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69da6274c58c81909c646eabed6f4f30 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e673a26c8481908f408fb6426aece9 completed April 20, 2026, 6:42 p.m.
Created at: April 11, 2026, 11:40 p.m.