Triple

T19246685
Position Surface form Disambiguated ID Type / Status
Subject Shepway E481277 entity
Predicate containsSettlement P847 FINISHED
Object Sandgate E397091 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: Sandgate | Statement: [Shepway, containsSettlement, Sandgate]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sandgate
Context triple: [Shepway, containsSettlement, Sandgate]
  • A. Sandgate
    Sandgate is a railway station serving the suburb of Sandgate in the Newcastle region of New South Wales, Australia.
  • B. Sandgate chosen
    Sandgate is a coastal village and suburb in Kent, England, known for its shingle beach, historic seafront, and proximity to the town of Folkestone.
  • C. Whitegate
    Whitegate is a small coastal village and port in East Cork, Ireland, known historically for its fishing heritage and nearby oil refinery.
  • D. Whitegate
    Whitegate is a residential suburb within the town of Chadderton in Greater Manchester, England.
  • E. Wallgate
    Wallgate is a street in the center of Wigan, England, known for giving its name to the nearby Wigan Wallgate railway station.
  • 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_69d8e8cd9d1081908a181d02b88b59b8 completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e5fb2daacc8190b8af99dee51f238d completed April 20, 2026, 10:08 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0705e0e9208190ab6857bdc61ad22e completed May 15, 2026, 11:39 a.m.
Created at: April 10, 2026, 1:27 p.m.