Triple

T19120019
Position Surface form Disambiguated ID Type / Status
Subject Autobahn A59 E468016 entity
Predicate roadNumber P1864 FINISHED
Object A59
A59 is a German autobahn that runs roughly north–south through North Rhine-Westphalia, connecting cities such as Duisburg, Düsseldorf, and Bonn.
 E1359462 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: A59 | Statement: [Autobahn A59, roadNumber, A59]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: A59
Context triple: [Autobahn A59, roadNumber, A59]
  • A. A59
    A59 is a major road in northern England that runs between Liverpool and York, passing through key towns such as Preston and Skipton.
  • B. A595
    The A595 is a primary road in Cumbria, England, running along the county’s western side and serving as a key route to coastal towns and the western Lake District.
  • C. A55
    A55 is a major Australian highway route designation used for sections of the Castlereagh Highway in New South Wales.
  • D. A55
    The A55 is a major road in North Wales that forms part of the key route along the north coast, linking towns such as Hawarden to the wider regional and national road network.
  • E. A509
    The A509 is a primary road in England that connects the town of Wellingborough to the A45 and A14 corridors, providing a key route through Northamptonshire and surrounding areas.
  • 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: A59
Triple: [Autobahn A59, roadNumber, A59]
Generated description
A59 is a German autobahn that runs roughly north–south through North Rhine-Westphalia, connecting cities such as Duisburg, Düsseldorf, and Bonn.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: A59
Target entity description: A59 is a German autobahn that runs roughly north–south through North Rhine-Westphalia, connecting cities such as Duisburg, Düsseldorf, and Bonn.
  • A. A59
    A59 is a major road in northern England that runs between Liverpool and York, passing through key towns such as Preston and Skipton.
  • B. A595
    The A595 is a primary road in Cumbria, England, running along the county’s western side and serving as a key route to coastal towns and the western Lake District.
  • C. A55
    A55 is a major Australian highway route designation used for sections of the Castlereagh Highway in New South Wales.
  • D. A55
    The A55 is a major road in North Wales that forms part of the key route along the north coast, linking towns such as Hawarden to the wider regional and national road network.
  • E. A509
    The A509 is a primary road in England that connects the town of Wellingborough to the A45 and A14 corridors, providing a key route through Northamptonshire and surrounding areas.
  • 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_69d8dd06a26481908039e2a1bae8c597 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e3c810808190a88d5c7859e7c650 completed April 20, 2026, 8:28 a.m.
NED1 Entity disambiguation (via context triple) batch_6a05e67400088190a58e085281a62a54 completed May 14, 2026, 3:12 p.m.
NEDg Description generation batch_6a05e74c4a248190b4e02f0c0d53f904 completed May 14, 2026, 3:16 p.m.
NED2 Entity disambiguation (via description) batch_6a05e84cbbac8190aa3e935e67cac797 completed May 14, 2026, 3:20 p.m.
Created at: April 10, 2026, 12:05 p.m.