Triple

T10885865
Position Surface form Disambiguated ID Type / Status
Subject Autoroute A10 E257042 entity
Predicate hasJunctionWith P1018 FINISHED
Object A71
A71 is a major French autoroute that runs through central France, connecting the Paris region to Clermont-Ferrand and linking with other key motorways.
 E890593 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: A71 | Statement: [Autoroute A10, hasJunctionWith, A71]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: A71
Context triple: [Autoroute A10, hasJunctionWith, A71]
  • A. A7
    A7 is a major European motorway designation used for key north–south and east–west highway routes in several countries.
  • B. A73
    A73 is a primary road in Scotland that connects several towns and serves as a key regional transport route.
  • C. A73
    A73 is a major German autobahn in Bavaria and Thuringia that links cities such as Lichtenfels with the broader national motorway network.
  • D. A75
    A75 is a major road designation used for important motorway and trunk routes in parts of Europe.
  • E. A705
    A705 is a regional road in the United Kingdom that provides a transport link to the town of Howden.
  • 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: A71
Triple: [Autoroute A10, hasJunctionWith, A71]
Generated description
A71 is a major French autoroute that runs through central France, connecting the Paris region to Clermont-Ferrand and linking with other key motorways.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: A71
Target entity description: A71 is a major French autoroute that runs through central France, connecting the Paris region to Clermont-Ferrand and linking with other key motorways.
  • A. A7
    A7 is a major European motorway designation used for key north–south and east–west highway routes in several countries.
  • B. A73
    A73 is a major German autobahn in Bavaria and Thuringia that links cities such as Lichtenfels with the broader national motorway network.
  • C. A73
    A73 is a primary road in Scotland that connects several towns and serves as a key regional transport route.
  • D. A75
    A75 is a major road designation used for important motorway and trunk routes in parts of Europe.
  • E. A705
    A705 is a regional road in the United Kingdom that provides a transport link to the town of Howden.
  • 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_69d6aa848804819081b2713ca0bedf06 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d751dd6a3c81909965ef774e8b7309 completed April 9, 2026, 7:14 a.m.
NED1 Entity disambiguation (via context triple) batch_69dff7ecf1c48190aef0d31ef03d1f88 completed April 15, 2026, 8:41 p.m.
NEDg Description generation batch_69e002709d38819099c4402d30824612 completed April 15, 2026, 9:26 p.m.
NED2 Entity disambiguation (via description) batch_69e005873ba48190b8c24c77611562fa completed April 15, 2026, 9:39 p.m.
Created at: April 8, 2026, 9:21 p.m.