Triple

T20735141
Position Surface form Disambiguated ID Type / Status
Subject College Street, Sydney E509681 entity
Predicate hasJunctionWith P1018 FINISHED
Object Oxford Street, Sydney 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: Oxford Street, Sydney | Statement: [College Street, Sydney, hasJunctionWith, Oxford Street, Sydney]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Oxford Street, Sydney
Context triple: [College Street, Sydney, hasJunctionWith, Oxford Street, Sydney]
  • A. Market Street, Sydney
    Market Street in Sydney is a major central business district thoroughfare known for its shopping precincts and proximity to landmarks such as the AMP Tower.
  • B. Macquarie Street, Sydney
    Macquarie Street, Sydney is a historic civic and parliamentary boulevard in central Sydney that houses key government institutions, including the New South Wales Parliament.
  • C. George Street, Sydney
    George Street, Sydney is one of the city's main historic thoroughfares, running through the central business district and lined with major commercial, retail, and heritage landmarks.
  • D. Pitt Street, Sydney
    Pitt Street, Sydney is a major commercial and retail thoroughfare in central Sydney, known for its shopping precincts, office towers, and proximity to key transport and tourist hubs.
  • E. Park Street, Sydney
    Park Street, Sydney is a major east–west thoroughfare in central Sydney that separates the northern and southern sections of Hyde Park.
  • 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: Oxford Street, Sydney
Target entity description: Oxford Street, Sydney is a major inner-city thoroughfare known for its vibrant nightlife, shopping, and role as the heart of Sydney’s LGBTQ+ community.
  • A. Market Street, Sydney
    Market Street in Sydney is a major central business district thoroughfare known for its shopping precincts and proximity to landmarks such as the AMP Tower.
  • B. Macquarie Street, Sydney
    Macquarie Street, Sydney is a historic civic and parliamentary boulevard in central Sydney that houses key government institutions, including the New South Wales Parliament.
  • C. George Street, Sydney
    George Street, Sydney is one of the city's main historic thoroughfares, running through the central business district and lined with major commercial, retail, and heritage landmarks.
  • D. Pitt Street, Sydney
    Pitt Street, Sydney is a major commercial and retail thoroughfare in central Sydney, known for its shopping precincts, office towers, and proximity to key transport and tourist hubs.
  • E. Park Street, Sydney
    Park Street, Sydney is a major east–west thoroughfare in central Sydney that separates the northern and southern sections of Hyde Park.
  • 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_69e0b4c589c08190834fb5d86d0efa2b completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c209348c819084a2f35f36378680 completed April 21, 2026, 12:17 a.m.
Created at: April 16, 2026, 12:31 p.m.