Triple

T18169177
Position Surface form Disambiguated ID Type / Status
Subject Mount Akagi E434973 entity
Predicate hasRoad P959 FINISHED
Object Akagi Skyline
Akagi Skyline is a scenic mountain road in Japan known for its winding route and panoramic views around Mount Akagi.
E1310026 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: Akagi Skyline | Statement: [Mount Akagi, hasRoad, Akagi Skyline]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Akagi Skyline
Context triple: [Mount Akagi, hasRoad, Akagi Skyline]
  • A. Ominato Base
    Ominato Base is a major Japan Maritime Self-Defense Force naval installation located in northern Honshu, serving as a strategic hub for maritime defense and patrol operations.
  • B. Akagi Daimyōjin
    Akagi Daimyōjin is a Shinto deity associated with Mount Akagi and revered as the principal kami of Akagi Shrine in Japan.
  • C. Norikura Skyline
    Norikura Skyline is a scenic high-altitude mountain road in Japan renowned for its panoramic views of the Northern Japan Alps and seasonal alpine landscapes.
  • D. AMAKUSA AIR
    AMAKUSA AIR is the radio callsign used by Amakusa Airlines, a regional Japanese carrier serving routes primarily within Kyushu.
  • E. Naikaku
    Naikaku is the Japanese term for the Cabinet, the executive branch of Japan’s national government headed by the Prime Minister.
  • 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: Akagi Skyline
Triple: [Mount Akagi, hasRoad, Akagi Skyline]
Generated description
Akagi Skyline is a scenic mountain road in Japan known for its winding route and panoramic views around Mount Akagi.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Akagi Skyline
Target entity description: Akagi Skyline is a scenic mountain road in Japan known for its winding route and panoramic views around Mount Akagi.
  • A. Ominato Base
    Ominato Base is a major Japan Maritime Self-Defense Force naval installation located in northern Honshu, serving as a strategic hub for maritime defense and patrol operations.
  • B. Akagi Daimyōjin
    Akagi Daimyōjin is a Shinto deity associated with Mount Akagi and revered as the principal kami of Akagi Shrine in Japan.
  • C. Norikura Skyline
    Norikura Skyline is a scenic high-altitude mountain road in Japan renowned for its panoramic views of the Northern Japan Alps and seasonal alpine landscapes.
  • D. AMAKUSA AIR
    AMAKUSA AIR is the radio callsign used by Amakusa Airlines, a regional Japanese carrier serving routes primarily within Kyushu.
  • E. Naikaku
    Naikaku is the Japanese term for the Cabinet, the executive branch of Japan’s national government headed by the Prime Minister.
  • 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_69d8b90b7a188190b3fc7b8d4a6cd20a completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4df53ef148190a32aad0253547645 completed April 19, 2026, 1:57 p.m.
NED1 Entity disambiguation (via context triple) batch_6a038fc6c5008190a5ade67801d6df75 completed May 12, 2026, 8:38 p.m.
NEDg Description generation batch_6a03914c5f6081908963548dc01a524a completed May 12, 2026, 8:45 p.m.
NED2 Entity disambiguation (via description) batch_6a03925c322081909d435251e869194d completed May 12, 2026, 8:49 p.m.
Created at: April 10, 2026, 10:30 a.m.