Triple

T7749018
Position Surface form Disambiguated ID Type / Status
Subject Province of Pisa E175706 entity
Predicate containsCity P294 FINISHED
Object Cascina E570916 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: Cascina | Statement: [Province of Pisa, containsCity, Cascina]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cascina
Context triple: [Province of Pisa, containsCity, Cascina]
  • A. Cascina chosen
    Cascina is a historic Tuscan town in central Italy, located near Pisa and known for its traditional woodworking and furniture-making industries.
  • B. Casa del Monte
    Casa del Monte is one of the guest houses within Hearst Castle in San Simeon, California, known for its Mediterranean Revival architecture and lavish historic interiors.
  • C. Capannole
    Capannole is a small locality or village that forms part of the municipality of Bucine in the Tuscany region of Italy.
  • D. Caserio
    Caserio is a surname most notably associated with Nick Caserio, an American football executive and general manager of the Houston Texans in the NFL.
  • E. Casa de Bandini
    Casa de Bandini is a historic 19th-century adobe residence and former social and political center located in Old Town San Diego, California.
  • 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_69c69960b3588190a53aa590d31d9544 completed March 27, 2026, 2:51 p.m.
NER Named-entity recognition batch_69c703affb6c8190adf4723dc1139edf completed March 27, 2026, 10:24 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8be53b3788190a850ce1aaaac3aaa completed March 29, 2026, 5:53 a.m.
Created at: March 27, 2026, 4:08 p.m.