Triple

T20068543
Position Surface form Disambiguated ID Type / Status
Subject George Heriot’s Hospital E499671 entity
Predicate locatedOn P40 FINISHED
Object Lauriston Place 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: Lauriston Place | Statement: [George Heriot’s Hospital, locatedOn, Lauriston Place]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lauriston Place
Context triple: [George Heriot’s Hospital, locatedOn, Lauriston Place]
  • A. Lauriston Place chosen
    Lauriston Place is a major street in Edinburgh, Scotland, known for its mix of historic and institutional buildings, including parts of the University of Edinburgh.
  • B. Blechynden Terrace
    Blechynden Terrace is a street in Southampton, England, located near Southampton Central railway station and forming part of the surrounding station area.
  • C. Windsor Place
    Windsor Place is a residential street in Brooklyn, New York, located near Prospect Park and served by nearby subway access.
  • D. Ramillies Place
    Ramillies Place is a small side street in central London, located just off Ramillies Street near Oxford Street in the City of Westminster.
  • E. Ranelagh Place
    Ranelagh Place is a central street in Liverpool, England, known for its proximity to major city landmarks and transport links.
  • 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_69da627770948190997f486f9a2e370f completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e6637ac3fc8190911063b979c3afb8 completed April 20, 2026, 5:33 p.m.
Created at: April 11, 2026, 3:39 p.m.