Triple

T17406022
Position Surface form Disambiguated ID Type / Status
Subject Golasecca culture E423215 entity
Predicate mainSite P423 FINISHED
Object Sesto Calende 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: Sesto Calende | Statement: [Golasecca culture, mainSite, Sesto Calende]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sesto Calende
Context triple: [Golasecca culture, mainSite, Sesto Calende]
  • A. Sesto Calende chosen
    Sesto Calende is a town in northern Italy known for significant archaeological finds from the Lepontic Celtic culture, particularly rich Iron Age burial sites.
  • B. Sesto
    Sesto is a central operatic character in Handel’s “Giulio Cesare,” portrayed as a young Roman seeking to avenge his father’s death.
  • C. Vinalia
    Vinalia was an ancient Roman festival dedicated to wine and the protection of the grape harvest, associated especially with Jupiter and Venus.
  • D. San Valentino alla Muta
    San Valentino alla Muta is a small alpine village in South Tyrol, northern Italy, known for its proximity to Lake Resia and its scenic mountain surroundings.
  • E. Santo Stefano
    Santo Stefano is a small, historically significant Italian island in the Tyrrhenian Sea, known for its former Bourbon-era prison and rugged volcanic landscape.
  • 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_69d889d7d27c819088486ce3f0627fa1 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e43b0750688190bb123634d7c7273e completed April 19, 2026, 2:16 a.m.
Created at: April 10, 2026, 5:45 a.m.