Triple

T12646811
Position Surface form Disambiguated ID Type / Status
Subject SoHo (Hong Kong) E302045 entity
Predicate locatedNear P294 FINISHED
Object Staunton Street NE NERFINISHED

How this triple was built (3 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: Staunton Street | Statement: [SoHo (Hong Kong), locatedNear, Staunton Street]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Staunton Street
Context triple: [SoHo (Hong Kong), locatedNear, Staunton Street]
  • A. Arlington Street
    Arlington Street is a major thoroughfare in Boston’s Back Bay neighborhood, running along the eastern edge of the Boston Public Garden and lined with historic buildings.
  • B. Coleman Street
    Coleman Street is a road in Singapore’s civic district known for its proximity to historic landmarks and government buildings.
  • C. Randolph Street
    Randolph Street is a major east–west thoroughfare in downtown Chicago known for connecting the Loop business district to the lakefront and cultural attractions.
  • D. Stall Street
    Stall Street is a central shopping and pedestrian thoroughfare in the historic city of Bath, England, lined with retail outlets and close to major landmarks such as the Roman Baths and Bath Abbey.
  • E. Salisbury Street
    Salisbury Street is a central thoroughfare in downtown Raleigh, North Carolina, known for running through the government district and connecting key civic and cultural landmarks.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Staunton Street
Target entity description: Staunton Street is a popular street in Hong Kong’s Central–Mid-Levels area known for its bars, restaurants, and proximity to the trendy SoHo district.
  • A. Arlington Street
    Arlington Street is a major thoroughfare in Boston’s Back Bay neighborhood, running along the eastern edge of the Boston Public Garden and lined with historic buildings.
  • B. Coleman Street
    Coleman Street is a road in Singapore’s civic district known for its proximity to historic landmarks and government buildings.
  • C. Randolph Street
    Randolph Street is a major east–west thoroughfare in downtown Chicago known for connecting the Loop business district to the lakefront and cultural attractions.
  • D. Stall Street
    Stall Street is a central shopping and pedestrian thoroughfare in the historic city of Bath, England, lined with retail outlets and close to major landmarks such as the Roman Baths and Bath Abbey.
  • E. Salisbury Street
    Salisbury Street is a central thoroughfare in downtown Raleigh, North Carolina, known for running through the government district and connecting key civic and cultural landmarks.
  • F. None of above. chosen

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_69d7bdec9f9c8190b4bac675b7588211 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d9614cefdc81908cfc4a4d04aa6eda completed April 10, 2026, 8:45 p.m.
Created at: April 9, 2026, 5:17 p.m.