Triple

T4447118
Position Surface form Disambiguated ID Type / Status
Subject Air Union E96315 entity
Predicate operatedRoute P18593 FINISHED
Object Paris–London E199941 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: Paris–London | Statement: [Air Union, operatedRoute, Paris–London]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Paris–London
Context triple: [Air Union, operatedRoute, Paris–London]
  • A. London–Paris chosen
    London–Paris is a major international rail route connecting the capitals of the United Kingdom and France via the Channel Tunnel.
  • B. London–Lyon
    London–Lyon is an international high-speed rail route linking the United Kingdom’s capital with the major city of Lyon in east-central France.
  • C. London–Marseille
    London–Marseille is a cross-European rail route linking the United Kingdom’s capital with the major port city in southern France, popular for leisure and holiday travel.
  • D. London–Brussels
    London–Brussels is a major international high-speed rail route linking the United Kingdom and Belgium via the Channel Tunnel.
  • E. London–Amsterdam
    London–Amsterdam is a major international rail route connecting the capital cities of the United Kingdom and the Netherlands.
  • 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_69b345415ba481908df738e7174448ba completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b355d31e10819086590b9f828d50b0 completed March 13, 2026, 12:09 a.m.
NED1 Entity disambiguation (via context triple) batch_69b61386df48819080e44a23b9d67d23 completed March 15, 2026, 2:03 a.m.
Created at: March 12, 2026, 11:32 p.m.