Triple

T20301935
Position Surface form Disambiguated ID Type / Status
Subject Green Line (MBTA) E505502 entity
Predicate serves P98 FINISHED
Object Brookline 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: Brookline | Statement: [Green Line (MBTA), serves, Brookline]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Brookline
Context triple: [Green Line (MBTA), serves, Brookline]
  • A. Brookline chosen
    Brookline is an affluent, historic suburban town directly bordering Boston, known for its tree-lined streets, excellent public schools, and vibrant residential neighborhoods.
  • B. Waltham
    Waltham is a village in North East Lincolnshire, England, situated near the seaside resort of Cleethorpes.
  • C. Dedham
    Dedham is a historic suburban town in eastern Massachusetts that serves as the county seat of Norfolk County and lies just southwest of Boston.
  • D. Dedham
    Dedham is a historic village in Essex, England, famed for its picturesque countryside and association with the painter John Constable.
  • E. Norwell
    Norwell is a suburban town in Plymouth County, Massachusetts, known for its residential character, conservation land, and location along the North River.
  • 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_69e0b4b8ab648190906e18538c250148 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6770d82b48190b21ce7c52ec6d5a0 completed April 20, 2026, 6:57 p.m.
Created at: April 16, 2026, 11:17 a.m.