Triple

T22899345
Position Surface form Disambiguated ID Type / Status
Subject George Weidenfeld E568265 entity
Predicate familyName P18 FINISHED
Object Weidenfeld 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: Weidenfeld | Statement: [George Weidenfeld, familyName, Weidenfeld]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Weidenfeld
Context triple: [George Weidenfeld, familyName, Weidenfeld]
  • A. Harcout
    Harcourt is a small rural town in central Victoria, Australia, known historically for its apple orchards and granite quarries.
  • B. Weidenfeld & Nicolson chosen
    Weidenfeld & Nicolson is a British publishing house known for its influential non-fiction and literary titles.
  • C. Bastei
    Bastei is a famous rock formation and viewpoint in Germany’s Saxon Switzerland National Park, overlooking the Elbe River and known for its dramatic sandstone cliffs and historic bridge.
  • D. Querido Verlag
    Querido Verlag is a renowned Dutch publishing house, historically significant for publishing works by exiled German-speaking authors during the Nazi era.
  • E. Faber
    Faber is a retired English professor in Ray Bradbury’s dystopian novel "Fahrenheit 451" who secretly mentors the protagonist and represents the value of literature and critical thought in a censored society.
  • 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_69e2458c23ec81908fa2570692c6614f completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f180155b1c8190a83eb6ec45387a1a completed April 29, 2026, 3:50 a.m.
Created at: April 17, 2026, 3:41 p.m.