Triple

T12236756
Position Surface form Disambiguated ID Type / Status
Subject A12 autoroute E291614 entity
Predicate connects P390 FINISHED
Object A13 autoroute E1014246 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: A13 autoroute | Statement: [A12 autoroute, connects, A13 autoroute]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: A13 autoroute
Context triple: [A12 autoroute, connects, A13 autoroute]
  • A. A13 autoroute chosen
    The A13 autoroute is a major French motorway linking Paris to Normandy, serving as a key route toward cities such as Rouen and Caen.
  • B. A14 autoroute
    The A14 autoroute is a French motorway serving as a key western approach into Paris, helping to connect the capital with the A13 and the La Défense business district.
  • C. A15 autoroute
    The A15 autoroute is a French motorway serving as a key link between Paris and the northwestern suburbs, helping to connect the capital with the broader Île-de-France region.
  • D. A12 autoroute
    The A12 autoroute is a short French motorway in the Île-de-France region that connects the A13 to the N10, helping link Paris to the southwestern suburbs and beyond.
  • E. A103 autoroute
    The A103 autoroute is a short French motorway in the eastern suburbs of Paris that links local traffic to the larger national autoroute network.
  • 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_69d6ab668acc8190963ba424049d6aee completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d91cb2892c81909a97b3ad6ec2c21b completed April 10, 2026, 3:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6c0d431308190be15e9d9dbee1eaf completed May 3, 2026, 3:28 a.m.
Created at: April 8, 2026, 9:51 p.m.