Triple

T20340644
Position Surface form Disambiguated ID Type / Status
Subject Bernardine E495729 entity
Predicate editedBy P1954 FINISHED
Object William Mace 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: William Mace | Statement: [Bernardine, editedBy, William Mace]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: William Mace
Context triple: [Bernardine, editedBy, William Mace]
  • A. William Mace chosen
    William Mace is a film editor known for his work on the 1955 historical crime drama "The Girl in the Red Velvet Swing."
  • B. George Macalister
    George Macalister was a 19th-century Australian politician who served as Premier of Queensland.
  • C. Charles Mawhood
    Charles Mawhood was a British Army officer best known for leading Crown forces against George Washington’s troops during the American Revolutionary War, particularly at the Battle of Princeton.
  • D. Charles McCallum
    Charles McCallum is an actor known for his role in the film "The Devil's Playground."
  • E. John Rymill
    John Rymill was an Australian polar explorer best known for leading the British Graham Land Expedition in the 1930s, which significantly advanced the mapping and understanding of the Antarctic Peninsula region.
  • 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_69e0b4a3320881909495ae8bc30bc2dc completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6783533a881909a12311bb9c66542 completed April 20, 2026, 7:02 p.m.
Created at: April 16, 2026, 11:23 a.m.