Triple

T21703817
Position Surface form Disambiguated ID Type / Status
Subject Foro Italico E535721 entity
Predicate hosts P186 FINISHED
Object Italian Open (tennis) 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: Italian Open (tennis) | Statement: [Foro Italico, hosts, Italian Open (tennis)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Italian Open (tennis)
Context triple: [Foro Italico, hosts, Italian Open (tennis)]
  • A. Italian Open
    The Italian Open is a professional golf tournament held in Italy that forms part of the European Tour schedule.
  • B. Italian Open chosen
    The Italian Open is a prestigious professional tennis tournament held annually in Rome, featuring top men’s and women’s players on outdoor clay courts as a key lead-up to the French Open.
  • C. Madrid Open
    The Madrid Open is a premier professional tennis tournament held annually in Madrid, Spain, featuring both ATP and WTA tours on outdoor clay courts.
  • D. Spanish Open
    The Spanish Open is a professional golf tournament held in Spain that forms part of the European Tour schedule.
  • E. French Open
    The French Open is one of tennis's four major Grand Slam tournaments, renowned for its clay courts and held annually at Roland Garros in Paris.
  • 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_69e0c46b44c0819088ab883ebd44e0e8 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ef9b82901c81909de242c920fbc164 completed April 27, 2026, 5:23 p.m.
Created at: April 16, 2026, 6:46 p.m.