Triple

T19966834
Position Surface form Disambiguated ID Type / Status
Subject Via San Lorenzo E479956 entity
Predicate hasNameInItalian P17612 FINISHED
Object Via San Lorenzo 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: Via San Lorenzo | Statement: [Via San Lorenzo, hasNameInItalian, Via San Lorenzo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Via San Lorenzo
Context triple: [Via San Lorenzo, hasNameInItalian, Via San Lorenzo]
  • A. Via San Lorenzo chosen
    Via San Lorenzo is a historic street in the center of Genoa, Italy, known for its medieval architecture and proximity to major city landmarks.
  • B. Via San Giovanni
    Via San Giovanni is a principal medieval street in San Gimignano, Italy, known for its historic buildings, shops, and as a main route through the town’s walled center.
  • C. Via San Leonardo
    Via San Leonardo is a historic, scenic road in the Arcetri area of Florence, Italy, known for its villas, greenery, and views over the city.
  • D. Via San Pietro
    Via San Pietro is a historic street in the old town of Trento, Italy, known for its traditional architecture and central location within the city’s medieval core.
  • E. Via San Carlo
    Via San Carlo is a street located near Piazza Municipio, likely forming part of the historic urban center around the main municipal square.
  • 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_69d8e523c19881909f9197037200dde6 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65bc5e41881908c1e8867820f1c0c completed April 20, 2026, 5 p.m.
Created at: April 10, 2026, 1:54 p.m.