Triple

T493630
Position Surface form Disambiguated ID Type / Status
Subject JST E10241 entity
Predicate usedByCity P4810 FINISHED
Object Toyama
Toyama is a coastal city in central Japan known as the capital of Toyama Prefecture, serving as a regional industrial and transportation hub on the Sea of Japan.
 E208642 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: Toyama | Statement: [JST, usedByCity, Toyama]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Toyama
Context triple: [JST, usedByCity, Toyama]
  • A. Niigata
    Niigata is a major coastal city in north-central Japan known for its important seaport on the Sea of Japan, rice production, and sake brewing.
  • B. Nagano
    Nagano is a city in central Japan best known internationally for hosting the 1998 Winter Olympic Games.
  • C. Shizuoka
    Shizuoka is a coastal city in central Japan known for its views of Mount Fuji, green tea production, and role as the capital of Shizuoka Prefecture.
  • D. Yamagata
    Yamagata is a city in northern Japan that serves as the capital of Yamagata Prefecture, known for its hot springs, winter sports, and cherry production.
  • E. Kameoka
    Kameoka is a city in Kyoto Prefecture, Japan, known for its rural landscapes, historical sites, and proximity to Kyoto.
  • 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: Toyama
Triple: [JST, usedByCity, Toyama]
Generated description
Toyama is a coastal city in central Japan known as the capital of Toyama Prefecture, serving as a regional industrial and transportation hub on the Sea of Japan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Toyama
Target entity description: Toyama is a coastal city in central Japan known as the capital of Toyama Prefecture, serving as a regional industrial and transportation hub on the Sea of Japan.
  • A. Niigata
    Niigata is a major coastal city in north-central Japan known for its important seaport on the Sea of Japan, rice production, and sake brewing.
  • B. Nagano
    Nagano is a city in central Japan best known internationally for hosting the 1998 Winter Olympic Games.
  • C. Shizuoka
    Shizuoka is a coastal city in central Japan known for its views of Mount Fuji, green tea production, and role as the capital of Shizuoka Prefecture.
  • D. Yamagata
    Yamagata is a city in northern Japan that serves as the capital of Yamagata Prefecture, known for its hot springs, winter sports, and cherry production.
  • E. Kameoka
    Kameoka is a city in Kyoto Prefecture, Japan, known for its rural landscapes, historical sites, and proximity to Kyoto.
  • 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_69a2e847df8481909239ec08ccf1e376 completed Feb. 28, 2026, 1:06 p.m.
NER Named-entity recognition batch_69a2f0fbfa408190aeb3b93996a35c00 completed Feb. 28, 2026, 1:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69add197c5248190ae37a11693975f97 completed March 8, 2026, 7:44 p.m.
NEDg Description generation batch_69add28a8f848190bf6ea0924e7dd9fc completed March 8, 2026, 7:48 p.m.
NED2 Entity disambiguation (via description) batch_69add37ad9a481908b2a1476a8d33091 completed March 8, 2026, 7:52 p.m.
Created at: Feb. 28, 2026, 1:12 p.m.