Triple

T15403780
Position Surface form Disambiguated ID Type / Status
Subject Green Line (MBTA) E368394 entity
Predicate serves P98 FINISHED
Object Downtown Boston E95364 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: Downtown Boston | Statement: [Green Line (MBTA), serves, Downtown Boston]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Downtown Boston
Context triple: [Green Line (MBTA), serves, Downtown Boston]
  • A. Downtown Boston chosen
    Downtown Boston is the city’s historic and commercial core, known for its dense cluster of landmarks, offices, and shopping areas.
  • B. South Boston
    South Boston is a densely populated waterfront neighborhood of Boston, Massachusetts, known for its strong Irish-American heritage and rapidly gentrifying urban landscape.
  • C. South Boston
    South Boston is an independent town in southern Virginia known for its historic downtown, former tobacco warehouses, and proximity to the Dan River.
  • D. Boston
    Boston is a World War II-era American light bomber aircraft, also known as the Douglas A-20 Havoc, used extensively by Allied air forces.
  • E. Boston
    Boston is a small town located in Wayne County, Indiana, in the United States.
  • 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_69d85a16c68c819099c1b547fbc87b32 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03e8fde64819082ec0c68df305561 completed April 16, 2026, 1:42 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff13584f8881908b2527c51f85ae28 completed May 9, 2026, 10:58 a.m.
Created at: April 10, 2026, 3:19 a.m.