Triple

T8721025
Position Surface form Disambiguated ID Type / Status
Subject Granville–Paris line E207010 entity
Predicate hasRouteDirection P15156 FINISHED
Object Paris–Granville
Paris–Granville is a regional railway service in France connecting the capital city Paris with the coastal town of Granville in Normandy.
 E752832 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: Paris–Granville | Statement: [Granville–Paris line, hasRouteDirection, Paris–Granville]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Paris–Granville
Context triple: [Granville–Paris line, hasRouteDirection, Paris–Granville]
  • A. Paris–Lille
    Paris–Lille is a major high-speed rail corridor in northern France connecting the capital Paris with the city of Lille.
  • B. Paris–Marseille
    Paris–Marseille is a major French intercity rail corridor linking the capital Paris with the Mediterranean port city of Marseille.
  • C. Paris–Caen–Cherbourg
    Paris–Caen–Cherbourg is a French intercity rail route linking the capital Paris with the Normandy cities of Caen and Cherbourg.
  • D. Paris–Bordeaux
    Paris–Bordeaux is a major high-speed rail corridor in France connecting the capital with the southwest, known for its fast TGV services.
  • E. Paris–Toulouse
    Paris–Toulouse is a major intercity rail corridor in France linking the capital Paris with the southwestern city of Toulouse.
  • 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: Paris–Granville
Triple: [Granville–Paris line, hasRouteDirection, Paris–Granville]
Generated description
Paris–Granville is a regional railway service in France connecting the capital city Paris with the coastal town of Granville in Normandy.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Paris–Granville
Target entity description: Paris–Granville is a regional railway service in France connecting the capital city Paris with the coastal town of Granville in Normandy.
  • A. Paris–Lille
    Paris–Lille is a major high-speed rail corridor in northern France connecting the capital Paris with the city of Lille.
  • B. Paris–Marseille
    Paris–Marseille is a major French intercity rail corridor linking the capital Paris with the Mediterranean port city of Marseille.
  • C. Paris–Caen–Cherbourg
    Paris–Caen–Cherbourg is a French intercity rail route linking the capital Paris with the Normandy cities of Caen and Cherbourg.
  • D. Paris–Bordeaux
    Paris–Bordeaux is a major high-speed rail corridor in France connecting the capital with the southwest, known for its fast TGV services.
  • E. Paris–Toulouse
    Paris–Toulouse is a major intercity rail corridor in France linking the capital Paris with the southwestern city of Toulouse.
  • 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_69ca835811d8819081ea00fd2a2c9a1c completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc5d03f0848190a50c77e5cd028ee7 completed March 31, 2026, 11:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69cf28f599a481908e93bc5b5c41296e completed April 3, 2026, 2:41 a.m.
NEDg Description generation batch_69cf2bd32cc881909ac8a61befa9929e completed April 3, 2026, 2:54 a.m.
NED2 Entity disambiguation (via description) batch_69cf2c69f83481909423858668d03a8b completed April 3, 2026, 2:56 a.m.
Created at: March 30, 2026, 6:36 p.m.