Triple

T5332904
Position Surface form Disambiguated ID Type / Status
Subject Clipper E123351 entity
Predicate usedOn P2367 FINISHED
Object County Connection E298676 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: County Connection | Statement: [Clipper, usedOn, County Connection]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: County Connection
Context triple: [Clipper, usedOn, County Connection]
  • A. County Connection chosen
    County Connection is a public transit agency serving bus and paratransit routes in central Contra Costa County in the San Francisco Bay Area.
  • B. AmericanConnection
    AmericanConnection was a regional airline brand used by American Airlines for its feeder services operated by various partner carriers.
  • C. Heartland Village
    Heartland Village is a primarily residential neighborhood located near the center of Staten Island in New York City.
  • D. The Gathering Place
    The Gathering Place is a popular nickname for Oahu, the most populous Hawaiian island and home to the state capital, Honolulu.
  • E. Rivertowns
    Rivertowns is an informal name for a group of historic, Hudson River–front villages and small cities in Westchester County, New York, known for their scenic waterfronts and commuter communities.
  • 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_69bd46477f9081909d242a327d749466 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd85ac8e10819088b6a9e02d927044 completed March 20, 2026, 5:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf18baeca081909acc11d0c6c89f6d completed March 21, 2026, 10:16 p.m.
Created at: March 20, 2026, 2 p.m.