Triple

T16177829
Position Surface form Disambiguated ID Type / Status
Subject Medici family E392609 entity
Predicate patronOf P2320 FINISHED
Object Michelangelo E14626 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: Michelangelo | Statement: [Medici family, patronOf, Michelangelo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michelangelo
Context triple: [Medici family, patronOf, Michelangelo]
  • A. Michelangelo chosen
    Michelangelo was a Renaissance master renowned as a sculptor, painter, and architect, celebrated for works such as the Sistine Chapel ceiling and the design of major religious structures in Rome.
  • B. Michelangelo
    Michelangelo is the fun-loving, pizza-obsessed, nunchuck-wielding Ninja Turtle known for his goofy humor and carefree attitude.
  • C. Michelangelo dei Conti
    Michelangelo dei Conti, better known as Pope Innocent XIII, was an 18th-century Italian pope who led the Catholic Church from 1721 to 1724.
  • D. Miguel Ángel
    Miguel Ángel is a Spanish businessman best known as the CEO and majority shareholder of Atlético Madrid football club.
  • E. Lorenzo Quinn
    Lorenzo Quinn is an Italian sculptor and former actor renowned for his expressive figurative sculptures, often exploring themes of love, faith, and the human condition.
  • 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_69d87f1d32208190942e4e499a80c18c completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e22059e7048190b4592cb1516b5f8d completed April 17, 2026, 11:58 a.m.
NED1 Entity disambiguation (via context triple) batch_69fffefe4dc08190a6cc43a448ae6554 completed May 10, 2026, 3:43 a.m.
Created at: April 10, 2026, 5:02 a.m.