Triple

T14428162
Position Surface form Disambiguated ID Type / Status
Subject canton of Schaffhausen E357749 entity
Predicate contains P35 FINISHED
Object Rhine Falls E634695 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: Rhine Falls | Statement: [canton of Schaffhausen, contains, Rhine Falls]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rhine Falls
Context triple: [canton of Schaffhausen, contains, Rhine Falls]
  • A. Rhine Falls chosen
    Rhine Falls is a spectacular and powerful waterfall in northern Switzerland, renowned as one of the largest waterfalls in Europe by volume.
  • B. Rhine Falls
    Rhine Falls is a rural locality within New South Wales, Australia, situated in the Snowy Monaro region known for its high-country landscapes and cool climate.
  • C. Trümmelbach Falls
    Trümmelbach Falls is a series of powerful glacier-fed waterfalls hidden inside a mountain in the Swiss Alps, accessible through tunnels and walkways.
  • D. Giessbach Falls
    Giessbach Falls is a spectacular multi-tiered waterfall in the Bernese Oberland region of Switzerland, cascading into Lake Brienz and accessible by historic funicular and hiking trails.
  • E. Vernooy Falls
    Vernooy Falls is a scenic multi-tiered waterfall located in the Catskill region of New York, popular for hiking and nature viewing.
  • 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_69d8279402a88190821ffa39ae15bccf completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de91154de881909266ae88d1545685 completed April 14, 2026, 7:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd5bcfa1d88190b59cefd3e305f55f completed May 8, 2026, 3:43 a.m.
Created at: April 10, 2026, 1:18 a.m.