Triple

T20774697
Position Surface form Disambiguated ID Type / Status
Subject Cornelia Funke E511324 entity
Predicate notableWork P4 FINISHED
Object Inkspell 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: Inkspell | Statement: [Cornelia Funke, notableWork, Inkspell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Inkspell
Context triple: [Cornelia Funke, notableWork, Inkspell]
  • A. Inkspell chosen
    Inkspell is the second novel in Cornelia Funke’s popular Inkworld fantasy series, continuing the story of Meggie and her family as they become further entangled in the magical book world first introduced in Inkheart.
  • B. Inkheart
    Inkheart is a 2008 fantasy adventure film, based on Cornelia Funke’s novel, about a man who can bring characters from books to life by reading aloud.
  • C. The Spell
    The Spell is a 1977 made-for-television horror film in which Lee Grant stars in a story about a bullied teenage girl who uses telekinesis for revenge.
  • D. The Spell
    The Spell is a subtitle of G.K. Chesterton’s metaphysical novel "Thursday; or, The Man Who Was Thursday," highlighting its enigmatic, almost magical atmosphere.
  • E. The Land of Spells
    The Land of Spells is a fantastical realm where magic, enchantments, and sorcery shape the world and its inhabitants.
  • 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_69e0b4cac7a48190a715cb3d545df2b4 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c26a39bc81909ca5d102056d8586 completed April 21, 2026, 12:18 a.m.
Created at: April 16, 2026, 12:37 p.m.