Triple

T20210471
Position Surface form Disambiguated ID Type / Status
Subject Cressida Cowell E493474 entity
Predicate name P16 FINISHED
Object Cressida Cowell 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: Cressida Cowell | Statement: [Cressida Cowell, name, Cressida Cowell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cressida Cowell
Context triple: [Cressida Cowell, name, Cressida Cowell]
  • A. Cressida Cowell chosen
    Cressida Cowell is a British children's author and illustrator best known for her "How to Train Your Dragon" book series, which inspired the popular animated film franchise.
  • B. Cornelia Funke
    Cornelia Funke is a German author best known for her fantasy novels for children and young adults, including the popular Inkheart trilogy.
  • C. Julie Herrod
    Julie Herrod is an American actress best known for her role as the young neighbor Gloria in the 1967 suspense film "Wait Until Dark."
  • D. Tessa Dahl
    Tessa Dahl is a British author and former actress, known for her novels and as the daughter of writer Roald Dahl and actress Patricia Neal.
  • E. Hannah Colfer
    Hannah Colfer is the sister of American actor and author Chris Colfer, known to fans through his public mentions of their close sibling relationship.
  • 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_69da6269614c8190bb40475d9d477358 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66ed5691c8190bf253b1d4ee6e88f completed April 20, 2026, 6:22 p.m.
Created at: April 11, 2026, 11:38 p.m.