Triple

T8192067
Position Surface form Disambiguated ID Type / Status
Subject A52 road E191333 entity
Predicate connects P390 FINISHED
Object Skegness E135844 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: Skegness | Statement: [A52 road, connects, Skegness]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Skegness
Context triple: [A52 road, connects, Skegness]
  • A. Skegness chosen
    Skegness is a seaside town and popular holiday resort on the east coast of England.
  • B. Cleethorpes
    Cleethorpes is a seaside resort town on the east coast of England, known for its sandy beaches, promenade, and traditional British holiday attractions.
  • C. Hornsea
    Hornsea is a small seaside town and former fishing village on the North Sea coast of the East Riding of Yorkshire in England, known for its beach, promenade, and nearby Hornsea Mere.
  • D. Mablethorpe
    Mablethorpe is a seaside town on the Lincolnshire coast of England, known for its sandy beaches and traditional holiday attractions.
  • E. Cromer
    Cromer is a small rural village located within the North Hertfordshire district of Hertfordshire, England.
  • 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_69ca82c5b6948190a583c096fb0a6c71 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb4da4a6f08190be8088a28d928341 completed March 31, 2026, 4:29 a.m.
NED1 Entity disambiguation (via context triple) batch_69cceda1b22c8190acc1a2cd0fe36b70 completed April 1, 2026, 10:04 a.m.
Created at: March 30, 2026, 5:42 p.m.