Triple

T4637782
Position Surface form Disambiguated ID Type / Status
Subject Marengo, Piedmont E101575 entity
Predicate near P350 FINISHED
Object Alessandria E238351 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: Alessandria | Statement: [Marengo, Piedmont, near, Alessandria]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Alessandria
Context triple: [Marengo, Piedmont, near, Alessandria]
  • A. Alessandria chosen
    Alessandria is a city in the Piedmont region of northwestern Italy, known as an important industrial and transportation hub.
  • B. Cuneo
    Cuneo is a city in the Piedmont region of northwestern Italy, known for its Alpine setting, agricultural traditions, and use of the Piedmontese language.
  • C. Biella
    Biella is a city in the Piedmont region of northern Italy, known for its textile industry and Alpine foothill setting.
  • D. Vercelli
    Vercelli is a historic city in northern Italy’s Piedmont region, known for its medieval architecture and important role in rice cultivation.
  • E. Ivrea
    Ivrea is a historic town in Italy’s Piedmont region, known for its medieval architecture, industrial heritage, and the famous Battle of the Oranges carnival.
  • 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_69bd43d2f1c081908cd4b7ec48ecc73d completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd5a64214481908a207e8070cc7a45 completed March 20, 2026, 2:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69be036d7aa081908b4b361dbae8ebc7 completed March 21, 2026, 2:33 a.m.
Created at: March 20, 2026, 1:13 p.m.