Triple

T18967885
Position Surface form Disambiguated ID Type / Status
Subject Middle Temple Lane E464088 entity
Predicate connects P390 FINISHED
Object Fleet Street 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: Fleet Street | Statement: [Middle Temple Lane, connects, Fleet Street]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fleet Street
Context triple: [Middle Temple Lane, connects, Fleet Street]
  • A. Fleet Street chosen
    Fleet Street is a historic thoroughfare in central London long associated with the British press and newspaper industry.
  • B. Livery Street
    Livery Street is a street, likely in an urban area, known for its commercial and architectural significance.
  • C. Guildhall Street
    Guildhall Street is a central thoroughfare in Cambridge, England, situated in the historic city centre near the Guildhall and key shopping and civic areas.
  • D. Caxton Street
    Caxton Street is a street in Westminster, central London, known for housing the historic Caxton Hall building.
  • E. Bermondsey Street
    Bermondsey Street is a historic and increasingly fashionable street in the London Borough of Southwark, known for its independent shops, restaurants, galleries, and proximity to attractions like Tower Bridge and London Bridge.
  • 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_69d8dcffc278819086792a4ebfddfafa completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d6172888819090a8b3cb1db20496 completed April 20, 2026, 7:30 a.m.
Created at: April 10, 2026, noon