Triple

T15457292
Position Surface form Disambiguated ID Type / Status
Subject The Hayes E371802 entity
Predicate connectsTo P845 FINISHED
Object St Mary Street E1412364 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: St Mary Street | Statement: [The Hayes, connectsTo, St Mary Street]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: St Mary Street
Context triple: [The Hayes, connectsTo, St Mary Street]
  • A. St Mary Street chosen
    St Mary Street is a major thoroughfare and popular shopping and nightlife street in the centre of Cardiff, Wales.
  • B. St Mary’s Street
    St Mary’s Street is a central street in Cambridge, England, situated by Great St Mary’s Church and close to several University of Cambridge colleges and buildings.
  • C. Wood Street
    Wood Street is a central thoroughfare in Cardiff, Wales, situated in the heart of the city’s commercial and transport district near Cardiff Central railway station.
  • D. Renshaw Street
    Renshaw Street is a major thoroughfare in central Liverpool, England, known for its mix of shops, eateries, and historic urban streetscape.
  • E. St Andrew's Street
    St Andrew's Street is a central thoroughfare in Cambridge, England, known for its historic university buildings, shops, and proximity to key city landmarks.
  • 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_69d85cc8bd308190886949510b42e764 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e03f146a2c8190882741af3ec15268 completed April 16, 2026, 1:44 a.m.
NED1 Entity disambiguation (via context triple) batch_6a099eba359c81909d95e777205be974 completed May 17, 2026, 10:55 a.m.
Created at: April 10, 2026, 3:31 a.m.