Triple

T17782304
Position Surface form Disambiguated ID Type / Status
Subject Margate E443927 entity
Predicate railConnection P848 FINISHED
Object Canterbury E72201 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: Canterbury | Statement: [Margate, railConnection, Canterbury]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Canterbury
Context triple: [Margate, railConnection, Canterbury]
  • A. Canterbury
    Canterbury is a large region on New Zealand’s South Island, centered on the city of Christchurch and known for its expansive plains, alpine scenery, and diverse communities.
  • B. Canterbury chosen
    Canterbury is a historic cathedral city in Kent, England, renowned for its medieval architecture and status as a major center of Christian pilgrimage.
  • C. Canterbury
    Canterbury is a renowned New Zealand-founded sportswear brand best known for producing high-performance rugby apparel and kits for top international teams.
  • D. Bristol
    Bristol is a small town located in Dane County in the U.S. state of Wisconsin.
  • E. Bristol
    Bristol is a small community within the town of East Gwillimbury in Ontario, Canada.
  • 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_69d8b9ef17708190bdf7e2adbf14ddc2 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e4872260b881908e77096500451816 completed April 19, 2026, 7:41 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0306e964fc81909aac3ab6a7ba0db6 completed May 12, 2026, 10:54 a.m.
Created at: April 10, 2026, 10:12 a.m.