Triple

T2490559
Position Surface form Disambiguated ID Type / Status
Subject Kokusai Ki-59 E52029 entity
Predicate manufacturer P490 FINISHED
Object Kokusai
Kokusai was a Japanese aircraft manufacturer known for producing military and transport planes before and during World War II.
 E272358 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: Kokusai | Statement: [Kokusai Ki-59, manufacturer, Kokusai]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kokusai
Context triple: [Kokusai Ki-59, manufacturer, Kokusai]
  • A. Nisshoki
    Nisshoki, more commonly known as the Hinomaru, is the national flag of Japan featuring a red sun disc centered on a white field.
  • B. Mibuchi
    Mibuchi is a Japanese surname borne by individuals such as Tadahiko Mibuchi.
  • C. Kantei
    Kantei is the official office and residence complex of Japan’s Prime Minister, serving as the central hub of the country’s executive government.
  • D. Awaji
    Awaji is a city located on Awaji Island in Japan, known for its scenic coastal landscapes, agriculture, and role as a gateway between Honshu and Shikoku.
  • E. Eichig
    Eichig is a small locality that forms part of the town of Lichtenfels in the Upper Franconia region of Bavaria, Germany.
  • 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: Kokusai
Triple: [Kokusai Ki-59, manufacturer, Kokusai]
Generated description
Kokusai was a Japanese aircraft manufacturer known for producing military and transport planes before and during World War II.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kokusai
Target entity description: Kokusai was a Japanese aircraft manufacturer known for producing military and transport planes before and during World War II.
  • A. Nisshoki
    Nisshoki, more commonly known as the Hinomaru, is the national flag of Japan featuring a red sun disc centered on a white field.
  • B. Mibuchi
    Mibuchi is a Japanese surname borne by individuals such as Tadahiko Mibuchi.
  • C. Kantei
    Kantei is the official office and residence complex of Japan’s Prime Minister, serving as the central hub of the country’s executive government.
  • D. Awaji
    Awaji is a city located on Awaji Island in Japan, known for its scenic coastal landscapes, agriculture, and role as a gateway between Honshu and Shikoku.
  • E. Eichig
    Eichig is a small locality that forms part of the town of Lichtenfels in the Upper Franconia region of Bavaria, Germany.
  • 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_69ab4955111c8190835bf619adec21ff completed March 6, 2026, 9:38 p.m.
NER Named-entity recognition batch_69abd18fe32081909580c6272a6013c5 completed March 7, 2026, 7:19 a.m.
NED1 Entity disambiguation (via context triple) batch_69af1f9111ec8190b464da14bc4be11e completed March 9, 2026, 7:29 p.m.
NEDg Description generation batch_69af209cb5dc8190b0a9870462205cd2 completed March 9, 2026, 7:33 p.m.
NED2 Entity disambiguation (via description) batch_69af2119cf10819083e0c66ae63eed2c completed March 9, 2026, 7:35 p.m.
Created at: March 6, 2026, 9:45 p.m.