Triple

T9369142
Position Surface form Disambiguated ID Type / Status
Subject Maryhill E225484 entity
Predicate near P350 FINISHED
Object Summerston E795063 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: Summerston | Statement: [Maryhill, near, Summerston]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Summerston
Context triple: [Maryhill, near, Summerston]
  • A. Summerston chosen
    Summerston is a residential suburb in the north-west of Glasgow, Scotland, known for its housing estates, local amenities, and proximity to open green spaces.
  • B. Springtown
    Springtown is a small rural community located within the township of Greater Madawaska in eastern Ontario, Canada.
  • C. Seagoville
    Seagoville is a small city in North Texas that functions as a suburban community within the greater Dallas–Fort Worth metropolitan area.
  • D. Wimberley
    Wimberley is a small, scenic town in central Texas known for its picturesque Hill Country landscapes, swimming holes, and artsy, tourist-friendly downtown.
  • E. Cedar Hill
    Cedar Hill is a suburban city in the Dallas–Fort Worth metropolitan area of Texas, known for its natural landscapes and proximity to Joe Pool Lake and Cedar Hill State Park.
  • 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_69ca842cbddc819099d71ecec48cf9e5 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd5080f55c8190bd5ca0dc0a4ea989 completed April 1, 2026, 5:06 p.m.
NED1 Entity disambiguation (via context triple) batch_69d100d68d28819082f366f3b5493cfb completed April 4, 2026, 12:15 p.m.
Created at: March 30, 2026, 7:43 p.m.