Triple

T21991998
Position Surface form Disambiguated ID Type / Status
Subject Matthew Garber E543111 entity
Predicate coStarredWith P14987 FINISHED
Object Karen Dotrice 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 Dotrice | Statement: [Matthew Garber, coStarredWith, Karen Dotrice]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Karen Dotrice
Context triple: [Matthew Garber, coStarredWith, Karen Dotrice]
  • A. Karen Dotrice chosen
    Karen Dotrice is a British former child actress best known for playing Jane Banks in Disney’s classic film "Mary Poppins."
  • B. Karen Daly
    Karen Daly is the sister of British television presenter Tess Daly.
  • C. Adrienne Keith
    Adrienne Keith is known as the spouse of British scientist, author, and television presenter Adam Hart-Davis.
  • D. Karen Hughes
    Karen Hughes is an American political consultant and communications strategist best known as a close confidante and senior adviser to President George W. Bush.
  • E. Karen Moss
    Karen Moss is the biological mother of television personality and fashion designer Nicole Richie.
  • 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_69e0c48136b081908831fa907cc02e18 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f1270e951081908deda039b47ca84b completed April 28, 2026, 9:30 p.m.
Created at: April 16, 2026, 8:05 p.m.