Triple

T3612076
Position Surface form Disambiguated ID Type / Status
Subject Cannon Street E76510 entity
Predicate connectsTo P845 FINISHED
Object King William Street E356187 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: King William Street | Statement: [Cannon Street, connectsTo, King William Street]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: King William Street
Context triple: [Cannon Street, connectsTo, King William Street]
  • A. King William Street chosen
    King William Street is a major thoroughfare in the City of London that connects key financial and commercial areas near London Bridge.
  • B. St George’s Street
    St George’s Street is a street in Hebden Bridge, West Yorkshire, England, known for housing the town’s historic Town Hall.
  • C. William Street
    William Street is a street in Lower Manhattan’s Financial District known for its proximity to major subway stations and financial institutions.
  • D. George Street
    George Street is a central thoroughfare in Manchester, England, known for running through the city's Chinatown district and hosting numerous East Asian restaurants and businesses.
  • E. George Street
    George Street is a notable thoroughfare running through Ottawa’s historic ByWard Market district, lined with shops, restaurants, and nightlife venues.
  • 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_69ad85da0ba481908b3b48c69efe2b98 completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc22e5b30819084184b730732c727 completed March 8, 2026, 6:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdf9f26be48190bf21b252a922ca69 completed March 21, 2026, 1:52 a.m.
Created at: March 8, 2026, 3:23 p.m.