Triple

T16823980
Position Surface form Disambiguated ID Type / Status
Subject Vermont E408966 entity
Predicate capital P234 FINISHED
Object Montpelier E4325 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: Montpelier | Statement: [Vermont, capital, Montpelier]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Montpelier
Context triple: [Vermont, capital, Montpelier]
  • A. Montpelier
    Montpelier is a residential inner-city area of Bristol, England, known for its diverse community, distinctive Victorian and Georgian architecture, and vibrant arts and music scene.
  • B. Montpelier
    Montpelier is the historic Virginia estate of James Madison, the fourth president of the United States and a key architect of the U.S. Constitution.
  • C. Montpelier
    Montpelier is a small unincorporated community in Muscatine County, Iowa, located along the Mississippi River.
  • D. Montpelier, Vermont chosen
    Montpelier, Vermont is the small, historic state capital of Vermont, known for its New England charm and distinctive gold-domed statehouse.
  • E. Augusta
    Augusta is the given first name of Ada Lovelace, the 19th-century mathematician often regarded as the world's first computer programmer.
  • 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_69d88394566c8190b3dcbdc72935f7fa completed April 10, 2026, 4:59 a.m.
NER Named-entity recognition batch_69e3b310ffec81908087e5aaacc4a7c2 completed April 18, 2026, 4:36 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00b29c170c81908fcc88c31e266ffb completed May 10, 2026, 4:30 p.m.
Created at: April 10, 2026, 5:23 a.m.