Triple

T19923146
Position Surface form Disambiguated ID Type / Status
Subject Niagara Falls, Ontario E478850 entity
Predicate hasAttraction P105 FINISHED
Object American Falls 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: American Falls | Statement: [Niagara Falls, Ontario, hasAttraction, American Falls]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: American Falls
Context triple: [Niagara Falls, Ontario, hasAttraction, American Falls]
  • A. American Falls chosen
    American Falls is one of the three major waterfalls that make up Niagara Falls, located on the U.S. side of the Niagara River between New York and Ontario.
  • B. Indian Falls
    Indian Falls is a scenic waterfall and popular hiking destination in the Adirondack High Peaks region of New York.
  • C. Big Falls
    Big Falls is a prominent waterfall on the Missouri River near Great Falls, Montana, known for its impressive drop and scenic views.
  • D. Shoshone Falls
    Shoshone Falls is a large waterfall in southern Idaho often called the "Niagara of the West" for its impressive height and volume.
  • E. Cascades Falls
    Cascades Falls is a scenic waterfall that serves as the main natural attraction within Cascades Falls Park.
  • 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_69d8e521855c8190b41871700afc8d6a completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e659c7be948190a65a1c78ba68dff3 completed April 20, 2026, 4:52 p.m.
Created at: April 10, 2026, 1:53 p.m.