Triple

T2652040
Position Surface form Disambiguated ID Type / Status
Subject Reims station E53921 entity
Predicate serves P98 FINISHED
Object city of Reims E9677 NE FINISHED

How this triple was built (2 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: city of Reims | Statement: [Reims station, serves, city of Reims]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: city of Reims
Context triple: [Reims station, serves, city of Reims]
  • A. Reims chosen
    Reims is a historic city in northeastern France known for its Gothic cathedral, role in French coronations, and significance during both World Wars.
  • B. Laon
    Laon is a historic hilltop city in northern France known for its well-preserved medieval architecture and impressive Gothic cathedral.
  • C. Troyes
    Troyes is a historic city in northeastern France, known for its well-preserved medieval old town, half-timbered houses, and Gothic churches.
  • D. Bourges, France
    Bourges, France is a historic city in central France known for its well-preserved medieval architecture and the UNESCO-listed Bourges Cathedral.
  • E. Saint-Denis
    Saint-Denis is a northern suburb of Paris known for its historic basilica, diverse population, and major sports venues including the Stade de France.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ab495e192081909c77b622e8e7e15a completed March 6, 2026, 9:38 p.m.
NER Named-entity recognition batch_69abd93071248190820197936e3167f7 completed March 7, 2026, 7:52 a.m.
NED1 Entity disambiguation (via context triple) batch_69afa052c91c8190abfd49dbc62a4448 completed March 10, 2026, 4:38 a.m.
Created at: March 6, 2026, 9:53 p.m.