Triple

T10846918
Position Surface form Disambiguated ID Type / Status
Subject Montpelier (Henry Knox Mansion) E256036 entity
Predicate town P3385 FINISHED
Object Thomaston E44194 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: Thomaston | Statement: [Montpelier (Henry Knox Mansion), town, Thomaston]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Thomaston
Context triple: [Montpelier (Henry Knox Mansion), town, Thomaston]
  • A. Thomaston
    Thomaston is a small city in central Georgia, United States, known for its historic downtown and role as a local commercial and cultural hub.
  • B. Thomaston
    Thomaston is a small incorporated village located on the North Shore of Long Island in Nassau County, New York.
  • C. Thomaston
    Thomaston is a small town located in Marengo County in the state of Alabama, United States.
  • D. Thomaston, Connecticut
    Thomaston, Connecticut is a small New England town in Litchfield County known for its historic clockmaking industry and traditional downtown.
  • E. Thomaston, Maine chosen
    Thomaston, Maine is a small coastal town in Knox County known for its historic architecture, shipbuilding heritage, and association with Revolutionary War general Henry Knox.
  • 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_69d6aa81a5d08190aa86689061d1ddd2 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d75113bc188190ac78df0c51d95de6 completed April 9, 2026, 7:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69dff7cc0d648190afb0ce80bac7f3dc completed April 15, 2026, 8:40 p.m.
Created at: April 8, 2026, 9:20 p.m.