Triple

T18133726
Position Surface form Disambiguated ID Type / Status
Subject M-1 Rail line E434081 entity
Predicate branding P1500 FINISHED
Object QLine 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: QLine | Statement: [M-1 Rail line, branding, QLine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: QLine
Context triple: [M-1 Rail line, branding, QLine]
  • A. QLine chosen
    QLine is a modern streetcar system serving downtown and Midtown Detroit, Michigan.
  • B. Q line
    The Q line is a New York City Subway service that runs along the BMT Brighton Line in Brooklyn and through Manhattan, connecting neighborhoods like Coney Island and Midtown.
  • C. A line
    The A line is a major New York City Subway service that runs primarily along the Eighth Avenue Line in Manhattan and extends into Brooklyn and Queens.
  • D. QLine streetcar
    The QLine streetcar is a modern streetcar system in Detroit, Michigan, providing fixed-rail public transit along the Woodward Avenue corridor.
  • E. Arrow line
    Arrow line is a commuter rail service in California’s Inland Empire that connects San Bernardino and Redlands as part of the regional Arrow (San Bernardino–Redlands) transit corridor.
  • 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_69d8b909e8cc81908df4cc2b8ea6d11f completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4de04321c81909c0b9d47757720fd completed April 19, 2026, 1:52 p.m.
Created at: April 10, 2026, 10:29 a.m.