Triple

T1560225
Position Surface form Disambiguated ID Type / Status
Subject South Shore E33301 entity
Predicate hasTown P847 FINISHED
Object Rockland E188157 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: Rockland | Statement: [South Shore, hasTown, Rockland]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rockland
Context triple: [South Shore, hasTown, Rockland]
  • A. Rockland chosen
    Rockland is a small suburban town in Plymouth County, Massachusetts, known for its residential character and proximity to Boston.
  • B. Cape Ann
    Cape Ann is a rocky peninsula on the northeastern coast of Massachusetts known for its historic fishing communities, maritime heritage, and scenic New England coastline.
  • C. Levant, Maine
    Levant, Maine is a small rural town located in Penobscot County in central Maine, known for its agricultural character and close proximity to the city of Bangor.
  • D. Yarmouth
    Yarmouth is a coastal town on Cape Cod in Massachusetts known for its beaches, historic villages, and tourism.
  • E. Yarmouth
    Yarmouth is a small historic port town and popular tourist destination on the western side of the Isle of Wight in England.
  • 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_69a885ef9cf48190b0af0f5ce3d02231 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a90885d6208190b4b7d6ad336d4d16 completed March 5, 2026, 4:37 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad719b6c988190a525539d1a29d8d4 completed March 8, 2026, 12:54 p.m.
Created at: March 4, 2026, 7:27 p.m.