Triple

T14142672
Position Surface form Disambiguated ID Type / Status
Subject Cardiff city centre road network E350464 entity
Predicate includesRoad P85887 FINISHED
Object Castle Street E173353 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: Castle Street | Statement: [Cardiff city centre road network, includesRoad, Castle Street]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Castle Street
Context triple: [Cardiff city centre road network, includesRoad, Castle Street]
  • A. Castle Street
    Castle Street is a central street in the historic market town of Farnham in Surrey, England, known for its Georgian architecture and local shops.
  • B. Castle Street chosen
    Castle Street is a major thoroughfare in central Cardiff, Wales, running past the historic Cardiff Castle and forming part of the city’s main civic and commercial area.
  • C. Castle Street
    Castle Street is a road in Carlisle, England, known for housing the Tullie House Museum and Art Gallery near the historic city centre and castle.
  • D. Castle Street
    Castle Street is a road in Cambridge, England, situated near the historic city center and close to landmarks such as Castle Hill.
  • E. Castle Street
    Castle Street is a major road in Glasgow, Scotland, known for serving key institutions including the Royal Infirmary of Glasgow.
  • 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_69d827865f608190b311820428ae027b completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de611ed3508190add37baa30d1d134 completed April 14, 2026, 3:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcdf18e3d08190b287e2da192d05eb completed May 7, 2026, 6:51 p.m.
Created at: April 10, 2026, 12:51 a.m.