Triple

T17832674
Position Surface form Disambiguated ID Type / Status
Subject Blackstone River E445300 entity
Predicate locatedIn P40 FINISHED
Object Millbury 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: Millbury | Statement: [Blackstone River, locatedIn, Millbury]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Millbury
Context triple: [Blackstone River, locatedIn, Millbury]
  • A. Millbury, Massachusetts chosen
    Millbury, Massachusetts is a small New England town in Worcester County known for its historic mill industry and suburban residential character.
  • B. Sedbury
    Sedbury is a village in Gloucestershire, England, situated near the Welsh border by the River Wye and the town of Chepstow.
  • C. Wrentham
    Wrentham is a small rural village in Suffolk, England, known for its traditional English countryside character and historic buildings.
  • D. West Boylston
    West Boylston is a small New England town in Worcester County, Massachusetts, known for its historic character and proximity to the Wachusett Reservoir.
  • E. Titchfield
    Titchfield is a village in Hampshire, England, known for hosting a major Office for National Statistics site and for its historic parish and nearby Titchfield Abbey.
  • 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_69d8b9f1a6d881909f024bc603111cdb completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e48d257414819088730f48ad7ab9ae completed April 19, 2026, 8:07 a.m.
Created at: April 10, 2026, 10:15 a.m.