Triple

T13041127
Position Surface form Disambiguated ID Type / Status
Subject Tōkai-Kanjō Expressway E327192 entity
Predicate connectsCity P4245 FINISHED
Object Toki
Toki is a city in Gifu Prefecture, Japan, known for its long-standing ceramics industry and production of Mino ware.
E1017624 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: Toki | Statement: [Tōkai-Kanjō Expressway, connectsCity, Toki]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Toki
Context triple: [Tōkai-Kanjō Expressway, connectsCity, Toki]
  • A. Togoshi
    Togoshi is a residential and commercial neighborhood in Tokyo’s Shinagawa ward, known for its traditional shopping streets and local atmosphere.
  • B. Tokoname
    Tokoname is a coastal city in Aichi Prefecture, Japan, historically renowned as one of the country’s Six Ancient Kilns for its distinctive ceramic and pottery production.
  • C. Taketa
    Taketa is a small historic city in Japan known for its scenic rural landscapes, hot springs, and castle ruins.
  • D. Taongi
    Taongi is a remote, uninhabited coral atoll in the Marshall Islands known for its rich marine biodiversity and relatively undisturbed natural environment.
  • E. Tokoro
    Tokoro is a coastal district of Kitami City in Hokkaido, Japan, known historically for its fishing industry and drift ice along the Sea of Okhotsk.
  • 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: Toki
Triple: [Tōkai-Kanjō Expressway, connectsCity, Toki]
Generated description
Toki is a city in Gifu Prefecture, Japan, known for its long-standing ceramics industry and production of Mino ware.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Toki
Target entity description: Toki is a city in Gifu Prefecture, Japan, known for its long-standing ceramics industry and production of Mino ware.
  • A. Togoshi
    Togoshi is a residential and commercial neighborhood in Tokyo’s Shinagawa ward, known for its traditional shopping streets and local atmosphere.
  • B. Tokoname
    Tokoname is a coastal city in Aichi Prefecture, Japan, historically renowned as one of the country’s Six Ancient Kilns for its distinctive ceramic and pottery production.
  • C. Taketa
    Taketa is a small historic city in Japan known for its scenic rural landscapes, hot springs, and castle ruins.
  • D. Taongi
    Taongi is a remote, uninhabited coral atoll in the Marshall Islands known for its rich marine biodiversity and relatively undisturbed natural environment.
  • E. Tokoro
    Tokoro is a coastal district of Kitami City in Hokkaido, Japan, known historically for its fishing industry and drift ice along the Sea of Okhotsk.
  • 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_69d8076e64308190904fb5c93517c901 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69d9804f0318819081516e2ca1de6797 completed April 10, 2026, 10:57 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6cbd5139c8190aaec6487f074f251 completed May 3, 2026, 4:15 a.m.
NEDg Description generation batch_69f6ce6278e081908864fba1db23ada0 completed May 3, 2026, 4:26 a.m.
NED2 Entity disambiguation (via description) batch_69f6cf547b188190b24c51e06a3b4d3c completed May 3, 2026, 4:30 a.m.
Created at: April 9, 2026, 8:56 p.m.