Triple

T2983406
Position Surface form Disambiguated ID Type / Status
Subject Lleida E80563 entity
Predicate transport P230 FINISHED
Object A-2 motorway E15062 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: A-2 motorway | Statement: [Lleida, transport, A-2 motorway]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: A-2 motorway
Context triple: [Lleida, transport, A-2 motorway]
  • A. A-4 motorway
    The A-4 motorway is a major Spanish highway that connects Madrid with the southern region of Andalusia, serving as a key route to cities like Córdoba and Seville.
  • B. A22 motorway
    The A22 motorway, also known as Via do Infante, is a major east–west toll highway in Portugal’s Algarve region that links coastal towns and connects to Spain.
  • C. A2 motorway chosen
    The A2 motorway is a major European highway that serves as a key route for long-distance traffic and connects with several important motorways, including the A22.
  • D. A20 motorway
    The A20 motorway is a major French highway running north–south through central and southwestern France, linking cities such as Vierzon, Limoges, and Toulouse.
  • E. A-49 motorway
    The A-49 motorway is a German autobahn in the state of Hesse that links the city of Kassel with the Schwalm-Eder region and is planned to be extended further south.
  • 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_69ad8b15f6ac8190be5fd16a33edcb4f completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad99c481fc81909971c96352a881b4 completed March 8, 2026, 3:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5281079fc8190a69ae43b14407736 completed March 14, 2026, 9:19 a.m.
Created at: March 8, 2026, 2:58 p.m.