Triple

T6817657
Position Surface form Disambiguated ID Type / Status
Subject Catherine Macmillan E156807 entity
Predicate relative P37 FINISHED
Object John Amery E611186 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: John Amery | Statement: [Catherine Macmillan, relative, John Amery]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Amery
Context triple: [Catherine Macmillan, relative, John Amery]
  • A. John Amery chosen
    John Amery was a British fascist and Nazi collaborator during World War II who was executed for high treason.
  • B. William Joyce
    William Joyce, infamously known as "Lord Haw-Haw," was a British fascist propagandist who broadcast Nazi radio programs to the United Kingdom during World War II.
  • C. Emanuel Reicher
    Emanuel Reicher was a prominent German stage actor and director of the late 19th and early 20th centuries, known for his influential work in classical and modern theater.
  • D. Henry Jacoby
    Henry Jacoby is an American economist and climate policy expert known for his work on energy and environmental economics at the Massachusetts Institute of Technology.
  • E. Leo Wiener
    Leo Wiener was a Polish-American linguist and scholar known for his work in Slavic languages and literature, and as the father of mathematician Norbert Wiener.
  • 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_69c688298a288190af3f285d57f76bbe completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d355b52081909f037cec76bdccf6 completed March 27, 2026, 6:58 p.m.
NED1 Entity disambiguation (via context triple) batch_69c723e458d881909fcea55915514eb1 completed March 28, 2026, 12:42 a.m.
Created at: March 27, 2026, 2:17 p.m.