Triple

T1669451
Position Surface form Disambiguated ID Type / Status
Subject Savin Hill E36089 entity
Predicate near P350 FINISHED
Object Columbia Point E33260 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: Columbia Point | Statement: [Savin Hill, near, Columbia Point]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Columbia Point
Context triple: [Savin Hill, near, Columbia Point]
  • A. Columbia Point chosen
    Columbia Point is a peninsula in the Dorchester neighborhood of Boston, Massachusetts, known for hosting major civic and educational institutions such as the Edward M. Kennedy Institute and the John F. Kennedy Presidential Library.
  • B. Columbia Point Marina Park
    Columbia Point Marina Park is a waterfront recreational area and boat marina located along the Columbia River in Richland, Washington.
  • C. Walker’s Point
    Walker’s Point is a historic neighborhood in Milwaukee, Wisconsin, known for its industrial roots, diverse community, and revitalized arts and dining scene.
  • D. Tuck’s Point
    Tuck’s Point is a scenic waterfront park and historic harbor area in Manchester-by-the-Sea, Massachusetts, known for its picturesque pier, bathhouse, and views of the Atlantic.
  • E. Union Bay
    Union Bay is a shallow, marshy inlet on the western shore of Lake Washington in Seattle, known for its wetlands and wildlife habitat.
  • 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_69a8861286808190939afff3ce8ee31e completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a90adf3d3c81909233e574e79b82a2 completed March 5, 2026, 4:47 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad7988bda081908a966ae1f589cb8f completed March 8, 2026, 1:28 p.m.
Created at: March 4, 2026, 7:29 p.m.