Triple

T22349232
Position Surface form Disambiguated ID Type / Status
Subject A10 motorway (Portugal) E552482 entity
Predicate roadNumber P1864 FINISHED
Object A10
A10 is a Portuguese motorway designation referring to a major controlled-access highway within Portugal’s national road network.
E890592 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: A10 | Statement: [A10 motorway (Portugal), roadNumber, A10]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: A10
Context triple: [A10 motorway (Portugal), roadNumber, A10]
  • A. A10
    The A10 is a major road in England that runs from London northwards through Hertfordshire and Cambridgeshire, forming a key route between the capital and East Anglia.
  • B. A10
    A10 is a major orbital motorway encircling Amsterdam in the Netherlands, connecting various national highways and providing primary access to the city.
  • C. A10
    A10 is the route designation for a major German autobahn that forms the orbital Berliner Ring encircling the city of Berlin.
  • D. A10
    A10 is a major Austrian motorway forming part of the Tauern Autobahn, an important north–south transit route through the Alps.
  • E. A10
    A10 is a designation commonly used for major motorways or expressways in various countries’ highway systems.
  • 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: A10
Triple: [A10 motorway (Portugal), roadNumber, A10]
Generated description
A10 is a Portuguese motorway designation referring to a major controlled-access highway within Portugal’s national road network.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: A10
Target entity description: A10 is a Portuguese motorway designation referring to a major controlled-access highway within Portugal’s national road network.
  • A. A10 chosen
    A10 is a designation commonly used for major motorways or expressways in various countries’ highway systems.
  • B. A10
    A10 is a major Italian motorway, also known as the Autostrada dei Fiori, connecting Genoa to the French border along the Ligurian coast.
  • C. A10
    A10 is a major orbital motorway encircling Amsterdam in the Netherlands, connecting various national highways and providing primary access to the city.
  • D. A10
    A10 is a major Austrian motorway forming part of the Tauern Autobahn, an important north–south transit route through the Alps.
  • E. A10
    A10 is the route designation for a major German autobahn that forms the orbital Berliner Ring encircling the city of Berlin.
  • F. None of above.

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.