Triple

T3678331
Position Surface form Disambiguated ID Type / Status
Subject Kingdom of Italy E78049 entity
Predicate capital P234 FINISHED
Object Pavia E109533 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: Pavia | Statement: [Kingdom of Italy, capital, Pavia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pavia
Context triple: [Kingdom of Italy, capital, Pavia]
  • A. Pavia
    Pavia is a municipality in the Philippine province of Iloilo known for its suburban character and proximity to Iloilo City.
  • B. Pavia chosen
    Pavia is a historic city in northern Italy, known for its ancient university, medieval architecture, and significant role in Lombardy’s cultural and academic life.
  • C. Vercelli
    Vercelli is a historic city in northern Italy’s Piedmont region, known for its medieval architecture and important role in rice cultivation.
  • D. Bergamo
    Bergamo is a historic city in northern Italy known for its medieval walled upper town, rich artistic heritage, and strategic location at the foothills of the Alps.
  • E. Parma
    Parma is a historic city in northern Italy renowned for its rich artistic heritage, architecture, and culinary traditions, including Parmigiano Reggiano cheese and Parma ham.
  • 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_69ad85e18c1c8190be8aafb227f39f48 completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc46599188190a046eddb0d85c483 completed March 8, 2026, 6:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69b589b716648190aeaead138203cbf9 completed March 14, 2026, 4:15 p.m.
Created at: March 8, 2026, 3:25 p.m.