Triple

T21555888
Position Surface form Disambiguated ID Type / Status
Subject Bruno Maderna E531888 entity
Predicate familyName P18 FINISHED
Object Maderna 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: Maderna | Statement: [Bruno Maderna, familyName, Maderna]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maderna
Context triple: [Bruno Maderna, familyName, Maderna]
  • A. Maderna chosen
    Maderna is an Italian surname most notably associated with Bruno Maderna, a prominent 20th-century composer and conductor linked to the postwar avant-garde.
  • B. Cesano Maderno
    Cesano Maderno is a town in the Lombardy region of northern Italy, located in the province of Monza and Brianza and part of the greater Milan metropolitan area.
  • C. Nervi
    Nervi is an Italian surname most famously associated with Pier Luigi Nervi, a pioneering structural engineer and architect known for his innovative use of reinforced concrete.
  • D. Nervi
    Nervi is a coastal district of Genoa in northwestern Italy, known for its scenic seaside promenade and historic villas and parks.
  • E. Molteni
    Molteni is a brand of Italian salami products known for producing traditional cured meats.
  • 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_69e0c460232c81908de2c3819d17c00e completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69eed2df48c88190894b6b08a5cb6390 completed April 27, 2026, 3:07 a.m.
Created at: April 16, 2026, 6:29 p.m.