Triple

T5483314
Position Surface form Disambiguated ID Type / Status
Subject Garisenda Tower E123517 entity
Predicate adjacentTo P224 FINISHED
Object Asinelli Tower E123516 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: Asinelli Tower | Statement: [Garisenda Tower, adjacentTo, Asinelli Tower]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Asinelli Tower
Context triple: [Garisenda Tower, adjacentTo, Asinelli Tower]
  • A. Asinelli Tower chosen
    Asinelli Tower is a famous medieval leaning tower in Bologna, Italy, known as one of the city’s iconic “Two Towers” and a prominent symbol of its historic skyline.
  • B. Torre Annunziata
    Torre Annunziata is a coastal city in southern Italy near Naples, known for its industrial port, archaeological sites linked to ancient Oplontis, and proximity to Mount Vesuvius.
  • C. Torre Guinigi
    Torre Guinigi is a medieval brick tower in Lucca, Italy, famous for the oak trees growing on its rooftop garden and its panoramic views over the city.
  • D. Campanile
    Campanile is a prominent Italianate-style bell tower that serves as a central architectural landmark within the village of Portmeirion in North Wales.
  • E. Campanile
    The Campanile is the iconic bell tower and one of the most recognizable architectural landmarks on the campus of Trinity College Dublin.
  • 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_69bd4648883481909e9775d43300c5fa completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd925deadc81908e193eeb75b63d90 completed March 20, 2026, 6:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf6c812d4c8190a22f76b787ab0f10 completed March 22, 2026, 4:13 a.m.
Created at: March 20, 2026, 2:10 p.m.