Triple

T4680364
Position Surface form Disambiguated ID Type / Status
Subject Millau Viaduct E103783 entity
Predicate partOf P40 FINISHED
Object A75 motorway E196064 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: A75 motorway | Statement: [Millau Viaduct, partOf, A75 motorway]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: A75 motorway
Context triple: [Millau Viaduct, partOf, A75 motorway]
  • A. A75 motorway chosen
    The A75 motorway is a major French highway running through central and southern France, known for connecting Clermont-Ferrand to Béziers and featuring the iconic Millau Viaduct.
  • B. A73 motorway
    The A73 motorway is a major German autobahn that runs through Bavaria and Thuringia, linking cities such as Nuremberg, Erlangen, Bamberg, and Suhl.
  • C. A73 motorway
    The A73 motorway is a major Dutch highway in the southeastern Netherlands that connects several cities and regions, including the area around Heumen.
  • D. A27 motorway
    The A27 motorway is a major north–south highway in the Netherlands that connects several key cities and regions in the central part of the country.
  • E. A7 motorway
    The A7 motorway is one of Germany's major north–south autobahns, running the length of the country and passing near cities such as Göttingen.
  • 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_69bd43debbf08190b4bc372e286ec234 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd636c105081908655ab384f539f38 completed March 20, 2026, 3:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69c870539eb08190936adcfbab395654 completed March 29, 2026, 12:20 a.m.
Created at: March 20, 2026, 1:16 p.m.