Triple

T12063014
Position Surface form Disambiguated ID Type / Status
Subject New Haven–New London E287220 entity
Predicate connectsCity P4245 FINISHED
Object New London E50140 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: New London | Statement: [New Haven–New London, connectsCity, New London]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: New London
Context triple: [New Haven–New London, connectsCity, New London]
  • A. New London
    New London is a small city in northeastern Missouri that serves as the administrative and governmental center of Ralls County.
  • B. New London
    New London is a small town located in Stanly County in the central region of North Carolina, United States.
  • C. New London, Connecticut chosen
    New London, Connecticut is a historic coastal city on the Thames River known for its deep-water port, maritime heritage, and role in the American Revolutionary era.
  • D. Bridgeport
    Bridgeport is a historic, working-class neighborhood on Chicago’s South Side known for its strong ethnic communities and proximity to the city’s major sports venues.
  • E. Bridgeport
    Bridgeport is a small unincorporated community in California’s Eastern Sierra region, known for its historic courthouse, scenic high-altitude valley, and access to outdoor recreation such as fishing, hiking, and hot springs.
  • 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_69d6ab4846e081908ee7bbd66a6d3459 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d9043f82248190b05692aa0dc178a8 completed April 10, 2026, 2:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe729766008190803c1dfef2c8c872 completed May 8, 2026, 11:32 p.m.
Created at: April 8, 2026, 9:48 p.m.