Triple

T20488799
Position Surface form Disambiguated ID Type / Status
Subject Interstate 87 E502682 entity
Predicate connects P390 FINISHED
Object Plattsburgh 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: Plattsburgh | Statement: [Interstate 87, connects, Plattsburgh]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Plattsburgh
Context triple: [Interstate 87, connects, Plattsburgh]
  • A. Plattsburgh, New York chosen
    Plattsburgh, New York is a small city in northeastern New York State on the western shore of Lake Champlain, known for its proximity to the Canadian border and its role as a regional commercial and educational center.
  • B. Utica
    Utica was an ancient Phoenician colony in North Africa that became one of the earliest and most important urban centers in the western Mediterranean.
  • C. Utica
    Utica is a small village in LaSalle County, Illinois, known as a gateway to the nearby Starved Rock State Park.
  • D. Utica
    Utica is a small town in Hinds County, Mississippi, known for its rural character and historic Southern setting.
  • E. Útica
    Útica is a small Colombian town known for its warm climate and location in the Gualivá region of the Cundinamarca department.
  • 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_69e0b4b0373881909dd3e9387f82eab4 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e69b5c6f84819087d813be3542ed33 completed April 20, 2026, 9:32 p.m.
Created at: April 16, 2026, 11:34 a.m.