Triple

T20210518
Position Surface form Disambiguated ID Type / Status
Subject The Gruffalo E493475 entity
Predicate author P4 FINISHED
Object Julia Donaldson 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: Julia Donaldson | Statement: [The Gruffalo, author, Julia Donaldson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Julia Donaldson
Context triple: [The Gruffalo, author, Julia Donaldson]
  • A. Julia Donaldson chosen
    Julia Donaldson is a British children's author and playwright best known for writing the rhyming picture book "The Gruffalo" and numerous other popular stories illustrated by Axel Scheffler.
  • B. Michael Rosen
    Michael Rosen is a British children's author, poet, and broadcaster known for his humorous and emotionally resonant works such as "We're Going on a Bear Hunt."
  • C. Frank Cottrell-Boyce
    Frank Cottrell-Boyce is a British screenwriter and author known for his work on films such as "24 Hour Party People" and "Millions," as well as for writing acclaimed children's books.
  • D. Michael Bond
    Michael Bond was a British author best known for creating the beloved children's character Paddington Bear.
  • E. Oliver Jeffers
    Oliver Jeffers is a Northern Irish artist, illustrator, and author best known for his distinctive picture books and visual storytelling.
  • 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.