Triple

T13828397
Position Surface form Disambiguated ID Type / Status
Subject Old Street E332314 entity
Predicate crosses P416 FINISHED
Object City Road E449206 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: City Road | Statement: [Old Street, crosses, City Road]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: City Road
Context triple: [Old Street, crosses, City Road]
  • A. City Road chosen
    City Road is a major thoroughfare in central London that runs through the boroughs of Islington and Hackney, connecting key commercial and historic areas including the vicinity of Bunhill Fields.
  • B. Chancery Lane
    Chancery Lane is a historic street in central London traditionally associated with the legal profession and home to many legal institutions and chambers.
  • C. London Bridge Street
    London Bridge Street is a central London road in the London Bridge area, known for hosting major landmarks and transport links, including The Shard and London Bridge station.
  • D. Drayton Street
    Drayton Street is a major north–south thoroughfare in Savannah, Georgia, running along the eastern edge of the historic Forsyth Park.
  • E. London Road
    London Road was the historic name of Manchester Piccadilly railway station, one of the main rail hubs in Manchester, England.
  • 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_69d81c5ae7c88190b0dd41bdafeb5999 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de02970df88190a1bf35dffd131d9d completed April 14, 2026, 9:02 a.m.
NED1 Entity disambiguation (via context triple) batch_69fd949b9fc481908c7717c412e05fac completed May 8, 2026, 7:45 a.m.
Created at: April 9, 2026, 10:13 p.m.