Triple

T5110839
Position Surface form Disambiguated ID Type / Status
Subject J. K. Rowling E115208 entity
Predicate twitterUsername P2943 FINISHED
Object jk_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: jk_rowling | Statement: [J. K. Rowling, twitterUsername, jk_rowling]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: jk_rowling
Context triple: [J. K. Rowling, twitterUsername, jk_rowling]
  • A. Bill Rowling
    Bill Rowling was a New Zealand Labour Party politician who served as Prime Minister in the mid-1970s.
  • B. J. K. Rowling chosen
    J. K. Rowling is a British author best known for writing the globally popular Harry Potter fantasy series.
  • C. de Potter
    de Potter is a Belgian noble family name historically associated with political and intellectual figures such as Louis de Potter.
  • D. Israel Potter
    Israel Potter is a lesser-known historical novel by Herman Melville that fictionalizes the life and adventures of an American Revolutionary War veteran.
  • E. Harry Potter
    Harry Potter is a young wizard who attends Hogwarts School of Witchcraft and Wizardry and becomes famous for surviving an attack by the dark wizard Lord Voldemort.
  • 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_69bd4441d1648190a54a533895041987 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd75ad362c8190b9cbded390aaea3c completed March 20, 2026, 4:28 p.m.
NED1 Entity disambiguation (via context triple) batch_69beef9de9c88190b06c5076e5eabe3e completed March 21, 2026, 7:21 p.m.
Created at: March 20, 2026, 1:41 p.m.