Triple

T18732113
Position Surface form Disambiguated ID Type / Status
Subject Lower Thames Street E458058 entity
Predicate connectsTo P845 FINISHED
Object Monument 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: Monument Street | Statement: [Lower Thames Street, connectsTo, Monument Street]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Monument Street
Context triple: [Lower Thames Street, connectsTo, Monument Street]
  • A. Monument Street chosen
    Monument Street is a road in the City of London, best known for leading to the Monument to the Great Fire of London near London Bridge.
  • B. Van Dorn Street
    Van Dorn Street is a major north–south thoroughfare in Alexandria, Virginia, serving residential, commercial, and commuter traffic in the city’s West End.
  • C. Locust Street
    Locust Street is a major east–west thoroughfare in Philadelphia, Pennsylvania, running through Center City and bordering landmarks such as Washington Square.
  • D. Pickett Street
    Pickett Street is a local roadway in Alexandria, Virginia, serving residential and commercial areas and connecting with several major city streets.
  • E. Cordova Street
    Cordova Street is a historic thoroughfare in Vancouver’s Gastown district, known for its heritage architecture and role in the city’s early urban development.
  • 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_69d8d393ba9c8190a8b03b04ddbb0a09 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e56d7854748190b66c4aaadfd67f29 completed April 20, 2026, 12:04 a.m.
Created at: April 10, 2026, 11:51 a.m.