Triple

T9369161
Position Surface form Disambiguated ID Type / Status
Subject Maryhill E225484 entity
Predicate hasGreenSpace P1495 FINISHED
Object Kelvin Walkway E562617 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: Kelvin Walkway | Statement: [Maryhill, hasGreenSpace, Kelvin Walkway]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kelvin Walkway
Context triple: [Maryhill, hasGreenSpace, Kelvin Walkway]
  • A. Kelvin Walkway chosen
    Kelvin Walkway is a scenic riverside path in Glasgow, Scotland, that follows the River Kelvin through parks and green spaces popular with walkers and cyclists.
  • B. Empress Walk
    Empress Walk is a mixed-use commercial and residential complex in North York, Toronto, featuring a shopping mall, cinema, and high-rise condominium towers.
  • C. Riverside Walk
    Riverside Walk is a popular, easy riverside trail in Zion National Park that follows the Virgin River through the scenic upper reaches of Zion Canyon.
  • D. Point Elizabeth Walkway
    Point Elizabeth Walkway is a coastal walking track on New Zealand’s West Coast known for its scenic clifftop views, native bush, and outlooks over the Tasman Sea.
  • E. Woodes Rogers Walk
    Woodes Rogers Walk is a waterfront promenade and tourist area in Nassau, Bahamas, lined with shops, restaurants, and historic landmarks along the harbor.
  • 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_69d0f40961e88190b12ab78edbebd252 completed April 4, 2026, 11:20 a.m.
Created at: March 30, 2026, 7:43 p.m.