Triple

T19124579
Position Surface form Disambiguated ID Type / Status
Subject Watling Street E468142 entity
Predicate connects P390 FINISHED
Object Roxeter NE NERFINISHED

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: Roxeter | Statement: [Watling Street, connects, Roxeter]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Roxeter
Context triple: [Watling Street, connects, Roxeter]
  • A. Roxeter chosen
    Roxeter is a historic settlement in Shropshire, England, known for its Roman origins and archaeological significance.
  • B. Essendine
    Essendine is a small village and civil parish in Rutland, England, known for its rural character and historic church.
  • C. Auriol
    Auriol is a French surname most notably borne by Vincent Auriol, the first president of the Fourth French Republic.
  • D. Umberleigh
    Umberleigh is a small rural village in North Devon, England, situated on the River Taw and served by a local railway station.
  • E. Ambrosden
    Ambrosden is a village and civil parish in Oxfordshire, England, located near the town of Bicester and known historically for its military connections.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8dd0796a48190b34ce4cd9d3f3be5 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e3cb9d6c81908a8706c1f33a6378 completed April 20, 2026, 8:28 a.m.
Created at: April 10, 2026, 12:05 p.m.