Triple

T8833117
Position Surface form Disambiguated ID Type / Status
Subject Amakusa Airfield E210194 entity
Predicate cityServed P82 FINISHED
Object Amakusa
Amakusa is a group of islands and a city in Kumamoto Prefecture, Japan, known for its coastal scenery, historical Christian heritage, and fishing communities.
 E849025 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: Amakusa | Statement: [Amakusa Airfield, cityServed, Amakusa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Amakusa
Context triple: [Amakusa Airfield, cityServed, Amakusa]
  • A. Omishima
    Omishima is a scenic island in Japan’s Seto Inland Sea, known for its cycling route on the Shimanami Kaido, historic Oyamazumi Shrine, and coastal landscapes.
  • B. Sumoto
    Sumoto is a coastal city located on Awaji Island in Japan, known for its hot springs, scenic views of the Seto Inland Sea, and citrus production.
  • C. Takashima
    Takashima is a lakeside city in western Shiga Prefecture, Japan, known for its scenic location along Lake Biwa and surrounding mountains.
  • D. Takashima
    Takashima is a prominent commercial and waterfront district in Nishi-ku, Yokohama, known for major shopping complexes and modern urban development.
  • E. Shimaore
    Shimaore is a Bantu language closely related to Comorian, widely spoken by the local population of Mayotte in the Indian Ocean.
  • 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: Amakusa
Triple: [Amakusa Airfield, cityServed, Amakusa]
Generated description
Amakusa is a group of islands and a city in Kumamoto Prefecture, Japan, known for its coastal scenery, historical Christian heritage, and fishing communities.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Amakusa
Target entity description: Amakusa is a group of islands and a city in Kumamoto Prefecture, Japan, known for its coastal scenery, historical Christian heritage, and fishing communities.
  • A. Omishima
    Omishima is a scenic island in Japan’s Seto Inland Sea, known for its cycling route on the Shimanami Kaido, historic Oyamazumi Shrine, and coastal landscapes.
  • B. Sumoto
    Sumoto is a coastal city located on Awaji Island in Japan, known for its hot springs, scenic views of the Seto Inland Sea, and citrus production.
  • C. Takashima
    Takashima is a lakeside city in western Shiga Prefecture, Japan, known for its scenic location along Lake Biwa and surrounding mountains.
  • D. Takashima
    Takashima is a prominent commercial and waterfront district in Nishi-ku, Yokohama, known for major shopping complexes and modern urban development.
  • E. Shimaore
    Shimaore is a Bantu language closely related to Comorian, widely spoken by the local population of Mayotte in the Indian Ocean.
  • 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_69ca8388549c819095fd94eadefbb007 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc605005788190a4df1fe317f3056a completed April 1, 2026, 12:01 a.m.
NED1 Entity disambiguation (via context triple) batch_69d56f68630081908564dca6c3c81f14 completed April 7, 2026, 8:56 p.m.
NEDg Description generation batch_69d570087a88819086f561041057ab66 completed April 7, 2026, 8:58 p.m.
NED2 Entity disambiguation (via description) batch_69d57056983c8190a264abcf7a271363 completed April 7, 2026, 9 p.m.
Created at: March 30, 2026, 6:47 p.m.