Triple

T16654739
Position Surface form Disambiguated ID Type / Status
Subject Sunwapta Falls E404698 entity
Predicate locatedBetween P1262 FINISHED
Object Jasper E401195 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: Jasper | Statement: [Sunwapta Falls, locatedBetween, Jasper]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jasper
Context triple: [Sunwapta Falls, locatedBetween, Jasper]
  • A. Jasper
    Jasper is a small city in northwestern Alabama known historically for its coal mining and role in the state's industrial development.
  • B. Jasper
    Jasper is a masculine given name of Persian origin meaning "treasurer," historically associated with one of the Three Wise Men and used in various English-speaking countries.
  • C. Jasper
    Jasper is one of Cruella de Vil’s bumbling henchmen who helps steal Dalmatian puppies in Disney’s "One Hundred and One Dalmatians."
  • D. Jasper chosen
    Jasper is a small resort town in Alberta, Canada, serving as a gateway and service hub for visitors to the surrounding Rocky Mountains and Jasper National Park.
  • E. Jasper
    Jasper is a cloud-based Internet of Things (IoT) platform company that provides tools for managing and monetizing connected devices and services.
  • 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_69d8838b5fbc81908c6575c132b82e80 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e37bf92de48190aaae3e93039b17f3 completed April 18, 2026, 12:41 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0084c6bf8c81909b376875ae038e3f completed May 10, 2026, 1:14 p.m.
Created at: April 10, 2026, 5:18 a.m.