Triple

T1900804
Position Surface form Disambiguated ID Type / Status
Subject Fosse Way E37684 entity
Predicate startPoint P389 FINISHED
Object Exeter E122858 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: Exeter | Statement: [Fosse Way, startPoint, Exeter]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Exeter
Context triple: [Fosse Way, startPoint, Exeter]
  • A. Exeter
    Exeter is a historic town in Rockingham County, New Hampshire, known for its colonial heritage and as the home of the prestigious Phillips Exeter Academy.
  • B. Exeter chosen
    Exeter is a historic cathedral city in Devon, England, known for its medieval architecture and role as a regional administrative and cultural center.
  • C. Bristol
    Bristol is a historic port city in southwest England known for its maritime heritage, vibrant cultural scene, and distinctive Georgian and Victorian architecture.
  • D. Exeter St Davids
    Exeter St Davids is the main railway station in Exeter, Devon, serving as a key hub on the Great Western Main Line in southwest England.
  • E. Brighton
    Brighton is a major seaside city on England’s south coast, renowned for its beach, pier, and vibrant cultural and nightlife scenes.
  • 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_69a8861be7148190a680937ec451a304 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69abb18c46c88190b10c05bf5c6a2d9c completed March 7, 2026, 5:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae030e55f88190a9996d785066ea20 completed March 8, 2026, 11:15 p.m.
Created at: March 4, 2026, 7:35 p.m.