Triple

T17877655
Position Surface form Disambiguated ID Type / Status
Subject Newport bus station E446997 entity
Predicate connectsTo P845 FINISHED
Object Sandown NE NERFINISHED

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: Sandown | Statement: [Newport bus station, connectsTo, Sandown]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sandown
Context triple: [Newport bus station, connectsTo, Sandown]
  • A. Sandown chosen
    Sandown is a seaside resort town on the southeast coast of England’s Isle of Wight, known for its sandy beach and traditional holiday attractions.
  • B. Sandown
    Sandown is an affluent commercial and residential suburb within Sandton, Johannesburg, known for its proximity to major business districts and shopping centers.
  • C. Penarth
    Penarth is a seaside town in the Vale of Glamorgan, Wales, known for its Victorian pier, esplanade, and role as a filming location for various British television series.
  • D. Cowes
    Cowes is a coastal town on the Isle of Wight in southern England, best known as a major international yachting and sailing centre.
  • E. Sandown Beach
    Sandown Beach is a popular sandy seaside destination on the Isle of Wight in England, known for its long promenade, family-friendly atmosphere, and traditional resort-town amenities.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8b9f4c22c819093c2680434472894 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e49aa6d24081908212e10d07c85a2b completed April 19, 2026, 9:04 a.m.
Created at: April 10, 2026, 10:18 a.m.