Triple

T23285723
Position Surface form Disambiguated ID Type / Status
Subject Etruscan Museum E588981 entity
Predicate regionServed P82 FINISHED
Object Volterra 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: Volterra | Statement: [Etruscan Museum, regionServed, Volterra]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Volterra
Context triple: [Etruscan Museum, regionServed, Volterra]
  • A. Volterra chosen
    Volterra is an ancient hilltop town in Tuscany, Italy, renowned for its Etruscan origins, medieval architecture, and traditional alabaster craftsmanship.
  • B. Osimo
    Osimo is a historic town in Italy’s Marche region, known for its medieval architecture and its role as the signing site of the Treaty of Osimo between Italy and Yugoslavia.
  • C. del Vasto
    Del Vasto is an Italian surname historically associated with the noble family of Adelaide del Vasto, a prominent medieval countess and regent in Sicily.
  • D. Loretano
    Loretano is a regional dialect of the Mojeño language spoken by Indigenous communities in the Bolivian lowlands.
  • E. Seregno
    Seregno is a town in the Lombardy region of northern Italy, known for its industrial activity and proximity to Milan.
  • 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_69e25d16e2c08190a291de254703129e completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f1964600888190b40ecbefdc8aec64 completed April 29, 2026, 5:25 a.m.
Created at: April 17, 2026, 4:59 p.m.