Triple

T9362112
Position Surface form Disambiguated ID Type / Status
Subject History on Trial E225304 entity
Predicate aboutPerson P2308 FINISHED
Object David Irving E248507 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: David Irving | Statement: [History on Trial, aboutPerson, David Irving]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: David Irving
Context triple: [History on Trial, aboutPerson, David Irving]
  • A. David Irving
    David Irving is the son of American novelist Clifford Irving, who was known for his controversial literary hoaxes.
  • B. David Irving chosen
    David Irving is a British author and Holocaust denier notorious for his pseudohistorical works on World War II and his legal battles over historical distortion.
  • C. Richard Evans
    Richard Evans is a researcher who contributed to the groundbreaking 2021 Nature paper on AlphaFold, the deep learning system for highly accurate protein structure prediction.
  • D. Thomas Kershaw
    Thomas Kershaw is a notable individual distinguished enough to be recognized as a prominent bearer of the surname Kershaw.
  • E. Anthony Julius
    Anthony Julius is a British solicitor and academic best known for representing Princess Diana in her divorce and for his writings on law, antisemitism, and literary criticism.
  • 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_69ca842bdd648190904131d58620d448 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd503ca7308190818f27f1faf94a53 completed April 1, 2026, 5:05 p.m.
NED1 Entity disambiguation (via context triple) batch_69d0f3eaf2208190967a3a8e82a4070b completed April 4, 2026, 11:20 a.m.
Created at: March 30, 2026, 7:42 p.m.