Triple

T22012141
Position Surface form Disambiguated ID Type / Status
Subject KHVN E543603 entity
Predicate cityServed P82 FINISHED
Object New Haven 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: New Haven | Statement: [KHVN, cityServed, New Haven]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: New Haven
Context triple: [KHVN, cityServed, New Haven]
  • A. New Haven
    New Haven is a small city in central Kentucky known for its historic railroad heritage and proximity to the Kentucky Railway Museum.
  • B. New Haven, Connecticut chosen
    New Haven, Connecticut is a historic coastal city in southern New England best known as the home of Yale University and a major center of education, culture, and research.
  • C. Hartford
    Hartford is the capital city of Connecticut and a historic center of insurance, government, and culture in the northeastern United States.
  • D. Hartford
    Hartford is a small city in eastern South Dakota that functions as a suburban community within the greater Sioux Falls metropolitan area.
  • E. West Haven
    West Haven is a coastal city in southern Connecticut known for its public beaches and shoreline along Long Island Sound.
  • 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_69e11e2db934819095556760c7d85e4d completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f127a520bc8190865f525a87255fb2 completed April 28, 2026, 9:33 p.m.
Created at: April 16, 2026, 8:22 p.m.