Triple

T19722140
Position Surface form Disambiguated ID Type / Status
Subject River Nore E473636 entity
Predicate flowsThrough P225 FINISHED
Object Thomastown 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: Thomastown | Statement: [River Nore, flowsThrough, Thomastown]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Thomastown
Context triple: [River Nore, flowsThrough, Thomastown]
  • A. Thomastown chosen
    Thomastown is a historic market town in County Kilkenny, Ireland, known for its medieval heritage and scenic location along the River Nore.
  • B. Thomastown
    Thomastown is a suburb in Melbourne, Victoria, Australia, known for its residential character and multicultural community.
  • C. Dormanstown
    Dormanstown is a residential area and suburb within the borough of Redcar and Cleveland in North Yorkshire, England.
  • D. Edgeworthstown
    Edgeworthstown is a small town in County Longford, Ireland, historically associated with the Anglo-Irish Edgeworth family and writer Maria Edgeworth.
  • E. Threemiletown
    Threemiletown is a small village in West Lothian, Scotland, situated near the A89 road between Linlithgow and Bathgate.
  • 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_69d8e517ebd48190979ee76723bcfadf completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e649f587d88190bf519fec7ce634d3 completed April 20, 2026, 3:44 p.m.
Created at: April 10, 2026, 1:46 p.m.