Triple

T19647892
Position Surface form Disambiguated ID Type / Status
Subject Gifted E471728 entity
Predicate producer P490 FINISHED
Object Karen Lunder 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: Karen Lunder | Statement: [Gifted, producer, Karen Lunder]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Karen Lunder
Context triple: [Gifted, producer, Karen Lunder]
  • A. Karen Lunder chosen
    Karen Lunder is a film producer known for her work on the drama adaptation "Hillbilly Elegy" and other feature films.
  • B. Sarah Charlesworth
    Sarah Charlesworth was an influential American conceptual artist and photographer associated with the Pictures Generation, known for her critical exploration of mass media imagery and representation.
  • C. Kiki Smith
    Kiki Smith is an American contemporary artist known for her multidisciplinary works exploring the human body, feminism, and mortality through sculpture, printmaking, and installation.
  • D. Sarah Benenson
    Sarah Benenson is a notable individual associated with the Benenson family name, recognized as a distinguished bearer of that surname.
  • E. Judith Cary Scott
    Judith Cary Scott is known primarily as the wife of American politician Charles Scott.
  • 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_69d8e51395348190ac1416d46dfc6db0 completed April 10, 2026, 11:54 a.m.
NER Named-entity recognition batch_69e64126cea88190a1a6929f46de4686 completed April 20, 2026, 3:07 p.m.
Created at: April 10, 2026, 1:44 p.m.