Triple

T13448332
Position Surface form Disambiguated ID Type / Status
Subject Sarek National Park E320542 entity
Predicate hasGlacier P4580 FINISHED
Object Mikka
Mikka is a glacier located within Sweden’s remote and mountainous Sarek National Park.
E1041125 NE FINISHED

How this triple was built (4 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: Mikka | Statement: [Sarek National Park, hasGlacier, Mikka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mikka
Context triple: [Sarek National Park, hasGlacier, Mikka]
  • A. Mikko
    Mikko is a Finnish given name commonly used for males, equivalent to the English name Michael.
  • B. Mikael Hakkarainen
    Mikael Hakkarainen is a Finnish professional ice hockey forward who has played in North American junior and professional leagues and was drafted by the Chicago Blackhawks in the NHL.
  • C. Mikko Heikka
    Mikko Heikka is a Finnish Lutheran bishop best known for serving as the inaugural bishop of the Diocese of Espoo in the Evangelical Lutheran Church of Finland.
  • D. Jussi Pakkanen
    Jussi Pakkanen is a Finnish software developer best known as the original author of the Meson build system.
  • E. Timo Aila
    Timo Aila is a computer scientist and researcher at NVIDIA known for his influential work in computer graphics and deep learning, including co-developing the StyleGAN generative adversarial network architecture.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Mikka
Triple: [Sarek National Park, hasGlacier, Mikka]
Generated description
Mikka is a glacier located within Sweden’s remote and mountainous Sarek National Park.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mikka
Target entity description: Mikka is a glacier located within Sweden’s remote and mountainous Sarek National Park.
  • A. Mikko
    Mikko is a Finnish given name commonly used for males, equivalent to the English name Michael.
  • B. Mikael Hakkarainen
    Mikael Hakkarainen is a Finnish professional ice hockey forward who has played in North American junior and professional leagues and was drafted by the Chicago Blackhawks in the NHL.
  • C. Mikko Heikka
    Mikko Heikka is a Finnish Lutheran bishop best known for serving as the inaugural bishop of the Diocese of Espoo in the Evangelical Lutheran Church of Finland.
  • D. Jussi Pakkanen
    Jussi Pakkanen is a Finnish software developer best known as the original author of the Meson build system.
  • E. Timo Aila
    Timo Aila is a computer scientist and researcher at NVIDIA known for his influential work in computer graphics and deep learning, including co-developing the StyleGAN generative adversarial network architecture.
  • F. None of above. chosen

Provenance (5 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_69d80761e6cc8190a90c844589998ecc completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbaef758b08190b9aa5ec7082cd417 completed April 12, 2026, 2:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69f73998221c8190a2d8982a3da28ec9 completed May 3, 2026, 12:03 p.m.
NEDg Description generation batch_69f73a598c6c81908420b00b665e3b08 completed May 3, 2026, 12:06 p.m.
NED2 Entity disambiguation (via description) batch_69f73e0e598c8190b030a45e658a5055 completed May 3, 2026, 12:22 p.m.
Created at: April 9, 2026, 9:41 p.m.