Triple

T9916703
Position Surface form Disambiguated ID Type / Status
Subject Morningstar Mill E185887 entity
Predicate near P350 FINISHED
Object Decew Falls waterfall E829975 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: Decew Falls waterfall | Statement: [Morningstar Mill, near, Decew Falls waterfall]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Decew Falls waterfall
Context triple: [Morningstar Mill, near, Decew Falls waterfall]
  • A. Decew Falls chosen
    Decew Falls is a scenic waterfall and historic site in St. Catharines, Ontario, known for its picturesque gorge, hiking trails, and preserved 19th-century mill complex.
  • B. Holloway Falls
    Holloway Falls is a novel by British author Neil Cross, known for its dark, character-driven storytelling and psychological depth.
  • C. Vernooy Falls
    Vernooy Falls is a scenic multi-tiered waterfall located in the Catskill region of New York, popular for hiking and nature viewing.
  • D. Sweet’s Falls
    Sweet’s Falls is a famous Class IV–V whitewater rapid on West Virginia’s Gauley River, known for its powerful drop and popularity among expert kayakers and rafters.
  • E. Bow Falls
    Bow Falls is a scenic, wide waterfall on the Bow River near Banff in Alberta, Canada, known for its powerful cascades and popularity with visitors.
  • 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_69ca829b45f481909040f7b99a1976ed completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cdb540195881908f25f7dde5c66a75 completed April 2, 2026, 12:16 a.m.
NED1 Entity disambiguation (via context triple) batch_69d228ae315c8190bedb2cbab0982118 completed April 5, 2026, 9:17 a.m.
Created at: March 30, 2026, 8:42 p.m.