Triple

T10788403
Position Surface form Disambiguated ID Type / Status
Subject John Boyle E254506 entity
Predicate appointedBy P257 FINISHED
Object James Madison E9994 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: James Madison | Statement: [John Boyle, appointedBy, James Madison]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: James Madison
Context triple: [John Boyle, appointedBy, James Madison]
  • A. James Madison chosen
    James Madison was the fourth president of the United States and a key architect of the U.S. Constitution and Bill of Rights.
  • B. James Monroe
    James Monroe was the fifth president of the United States, best known for the Monroe Doctrine and for overseeing an era of national expansion and relative political unity in the early 19th century.
  • C. David Madison
    David Madison is the given first name of Madison Cawthorn, an American politician and former U.S. Representative from North Carolina.
  • D. Jefferson
    Jefferson is a small city in northeastern Georgia that serves as the county seat of Jackson County and lies within the state's historic gold-mining region.
  • E. Jefferson
    Jefferson is a domestic cat known by the given name "Jefferson."
  • 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_69d6aa609f008190a294200aefcb7bd5 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d732d65fcc8190ab5573a861409c56 completed April 9, 2026, 5:02 a.m.
NED1 Entity disambiguation (via context triple) batch_69de55bb98ec8190914031643c1c7a97 completed April 14, 2026, 2:56 p.m.
Created at: April 8, 2026, 9:17 p.m.