Triple

T5062798
Position Surface form Disambiguated ID Type / Status
Subject Brasenose College, Oxford E114063 entity
Predicate hasNotableAlumni P51 FINISHED
Object William Golding E119014 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: William Golding | Statement: [Brasenose College, Oxford, hasNotableAlumni, William Golding]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: William Golding
Context triple: [Brasenose College, Oxford, hasNotableAlumni, William Golding]
  • A. William Golding chosen
    William Golding was a British novelist and Nobel Prize laureate best known for his allegorical novel "Lord of the Flies."
  • B. Anthony Burgess
    Anthony Burgess was a British novelist, critic, and composer best known for his dystopian novel "A Clockwork Orange."
  • C. Nevil Shute
    Nevil Shute was a British-born novelist and aeronautical engineer best known for his post-apocalyptic novel "On the Beach" and other mid-20th-century popular fiction.
  • D. Malcolm Lowry
    Malcolm Lowry was a British novelist and poet best known for his modernist masterpiece "Under the Volcano," a tragic portrait of an alcoholic British consul in Mexico.
  • E. David Herbert
    David Herbert is a renowned American percussionist best known for his role as principal timpanist with major U.S. orchestras.
  • 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_69bd443c0c8c81908663b77afb28e165 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd7475be3c819085cde8ec544c407e completed March 20, 2026, 4:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69bea497fed0819098746fd8917f041c completed March 21, 2026, 2 p.m.
Created at: March 20, 2026, 1:38 p.m.