Triple

T5830392
Position Surface form Disambiguated ID Type / Status
Subject Harry Potter and the Deathly Hallows E129330 entity
Predicate author P4 FINISHED
Object J. K. Rowling E115208 NE FINISHED

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: J. K. Rowling | Statement: [Harry Potter and the Deathly Hallows, author, J. K. Rowling]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: J. K. Rowling
Context triple: [Harry Potter and the Deathly Hallows, author, J. K. Rowling]
  • A. J. K. Rowling chosen
    J. K. Rowling is a British author best known for writing the globally popular Harry Potter fantasy series.
  • B. Bill Rowling
    Bill Rowling was a New Zealand Labour Party politician who served as Prime Minister in the mid-1970s.
  • C. T. H. White
    T. H. White was a British author best known for his Arthurian fantasy series "The Once and Future King."
  • D. Dodie Smith
    Dodie Smith was an English novelist and playwright best known for writing the children's classic "The Hundred and One Dalmatians."
  • E. Cornelia Funke
    Cornelia Funke is a German author best known for her fantasy novels for children and young adults, including the popular Inkheart trilogy.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69c00849d55481908b4f9f5543e0bf6d completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c0346905848190a8f541401da05604 completed March 22, 2026, 6:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69c09866fd248190b4248a993051b732 completed March 23, 2026, 1:33 a.m.
Created at: March 22, 2026, 3:54 p.m.