Triple

T7203744
Position Surface form Disambiguated ID Type / Status
Subject Nespresso E148612 entity
Predicate competitor P1375 FINISHED
Object Illy E73185 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: Illy | Statement: [Nespresso, competitor, Illy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Illy
Context triple: [Nespresso, competitor, Illy]
  • A. Dozza
    Dozza is a picturesque medieval hilltop village in Italy’s Emilia-Romagna region, renowned for its castle and open-air mural art.
  • B. Lavazza chosen
    Lavazza is a major Italian coffee company renowned worldwide for its espresso blends and coffee products.
  • C. Caffè Torino
    Caffè Torino is a historic and elegant café in Turin, Italy, renowned for its classic Belle Époque atmosphere and role as a traditional meeting place for locals and visitors.
  • D. Federico Caffè
    Federico Caffè was an influential Italian economist and academic known for his work on welfare economics, Keynesian theory, and social justice in economic policy.
  • E. Caffa
    Caffa is the historical name of the Crimean port city now known as Feodosia, which was a major Genoese trading colony and a key Black Sea commercial hub in the Middle Ages.
  • 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_69c687e8cf188190b5f3ecffd681f04e completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6e94bfb2c81909ab492757435fce4 completed March 27, 2026, 8:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7bfb5e27c8190867fb4968dea2e4e completed March 28, 2026, 11:47 a.m.
Created at: March 27, 2026, 2:52 p.m.