Triple

T21994313
Position Surface form Disambiguated ID Type / Status
Subject The Great Gilly Hopkins E543164 entity
Predicate authorOfSourceWork P2353 FINISHED
Object Katherine Paterson 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: Katherine Paterson | Statement: [The Great Gilly Hopkins, authorOfSourceWork, Katherine Paterson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Katherine Paterson
Context triple: [The Great Gilly Hopkins, authorOfSourceWork, Katherine Paterson]
  • A. Katherine Paterson chosen
    Katherine Paterson is an acclaimed American author of children's and young adult literature, best known for novels such as "Bridge to Terabithia" and "Jacob Have I Loved."
  • B. Lucille Findley
    Lucille Findley was the wife of longtime U.S. Congressman and author Paul Findley.
  • C. Natalie Babbitt
    Natalie Babbitt was an American author and illustrator of children’s books, best known for her classic fantasy novel "Tuck Everlasting."
  • D. Wendelin Van Draanen
    Wendelin Van Draanen is an American author best known for her young adult and children’s novels, including the popular book "Flipped."
  • E. Margaret Chodos-Irvine
    Margaret Chodos-Irvine is an American illustrator and printmaker known for her distinctive, textured artwork in children’s books.
  • 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_69e11e2c814c8190837d072789000486 completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f127639bf48190800b3fa3c1527983 completed April 28, 2026, 9:32 p.m.
Created at: April 16, 2026, 8:17 p.m.