Triple

T17743166
Position Surface form Disambiguated ID Type / Status
Subject Bill Lowry E442914 entity
Predicate name P16 FINISHED
Object Bill Lowry 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: Bill Lowry | Statement: [Bill Lowry, name, Bill Lowry]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bill Lowry
Context triple: [Bill Lowry, name, Bill Lowry]
  • A. Bill Lowry chosen
    Bill Lowry is a person notable enough to be recognized as a prominent bearer of the surname Lowry.
  • B. David Low
    David Low was a prominent New Zealand-born political cartoonist renowned for his influential anti-fascist cartoons during the mid-20th century.
  • C. Peter Lowe
    Peter Lowe was a Scottish surgeon of the late 16th and early 17th centuries who played a key role in professionalizing medical practice in Glasgow.
  • D. Frank Lowe
    Frank Lowe was an American free jazz saxophonist known for his intense, avant-garde style and collaborations with leading figures of the 1960s and 1970s jazz avant-garde.
  • E. Wilson Lowry
    Wilson Lowry was a prominent English engraver of the late 18th and early 19th centuries, known for his detailed work on scientific and architectural illustrations.
  • 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_69d8b9ed3a2081909b2ec0d4dd2f4c37 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e47ace58988190b927ca29af7a8b77 completed April 19, 2026, 6:48 a.m.
Created at: April 10, 2026, 10:09 a.m.