Triple

T22349182
Position Surface form Disambiguated ID Type / Status
Subject A27 motorway (Portugal) E552480 entity
Predicate roadNumber P1864 FINISHED
Object A27
A27 is a Portuguese motorway that connects the city of Viana do Castelo to the interior Minho region in northern Portugal.
 E1532711 NE FINISHED

How this triple was built (4 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: A27 | Statement: [A27 motorway (Portugal), roadNumber, A27]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: A27
Context triple: [A27 motorway (Portugal), roadNumber, A27]
  • A. A27
    A27 is a major east–west trunk road on the south coast of England, linking key towns and cities between East Sussex and Hampshire.
  • B. A22
    A22 is a major Portuguese motorway, commonly known as Via do Infante, that runs across the Algarve region in southern Portugal.
  • C. A28
    A28 is a major Dutch motorway that runs through the northeastern Netherlands, connecting several cities including Hoogeveen.
  • D. A28
    A28 is a major Portuguese motorway that runs along the northwest coast, connecting Porto to Viana do Castelo and the Spanish border.
  • E. A26
    A26 is a Portuguese motorway designated as part of the country's national high-speed road network.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: A27
Triple: [A27 motorway (Portugal), roadNumber, A27]
Generated description
A27 is a Portuguese motorway that connects the city of Viana do Castelo to the interior Minho region in northern Portugal.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: A27
Target entity description: A27 is a Portuguese motorway that connects the city of Viana do Castelo to the interior Minho region in northern Portugal.
  • A. A27
    A27 is a major east–west trunk road on the south coast of England, linking key towns and cities between East Sussex and Hampshire.
  • B. A22
    A22 is a major Portuguese motorway, commonly known as Via do Infante, that runs across the Algarve region in southern Portugal.
  • C. A28
    A28 is a major Portuguese motorway that runs along the northwest coast, connecting Porto to Viana do Castelo and the Spanish border.
  • D. A28
    A28 is a major Dutch motorway that runs through the northeastern Netherlands, connecting several cities including Hoogeveen.
  • E. A26
    A26 is a Portuguese motorway designated as part of the country's national high-speed road network.
  • F. None of above. chosen

Provenance (5 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_69e11e4a0ad08190a385b4d343cf6524 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f1579a1c308190ae2174f99ae317ab completed April 29, 2026, 12:58 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0ae05844948190b13a0e927f2a1c1f completed May 18, 2026, 9:48 a.m.
NEDg Description generation batch_6a0ae2e2883c81908a6fea37f8db7f1a completed May 18, 2026, 9:58 a.m.
NED2 Entity disambiguation (via description) batch_6a0ae3855838819080bf6883946b62f7 completed May 18, 2026, 10:01 a.m.
Created at: April 16, 2026, 8:43 p.m.