Triple

T6200381
Position Surface form Disambiguated ID Type / Status
Subject Ryukyu Kingdom E138613 entity
Predicate predecessor P97 FINISHED
Object Nanzan
Nanzan was one of the three rival polities on Okinawa Island during the Sanzan period, which was eventually unified into the Ryukyu Kingdom.
 E578616 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: Nanzan | Statement: [Ryukyu Kingdom, predecessor, Nanzan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Nanzan
Context triple: [Ryukyu Kingdom, predecessor, Nanzan]
  • A. Meijō
    Meijō is the Japanese name for Nagoya Castle, a historic and iconic samurai-era fortress in Nagoya, Japan.
  • B. Nanbu
    Nanbu is a town in Shizuoka Prefecture, Japan, known for its rural landscape and location near the border with Yamanashi Prefecture.
  • C. Fujinomiya
    Fujinomiya is a city in Shizuoka Prefecture, Japan, known as a major gateway to Mount Fuji and for its scenic views of the iconic volcano.
  • D. Isehara
    Isehara is a city in Kanagawa Prefecture, Japan, known as a residential and industrial area with access to nearby natural attractions such as the Tanzawa Mountains.
  • E. Higashiyamato
    Higashiyamato is a suburban city in western Tokyo, Japan, known for its residential neighborhoods and proximity to the Tama region’s parks and green spaces.
  • 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: Nanzan
Triple: [Ryukyu Kingdom, predecessor, Nanzan]
Generated description
Nanzan was one of the three rival polities on Okinawa Island during the Sanzan period, which was eventually unified into the Ryukyu Kingdom.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Nanzan
Target entity description: Nanzan was one of the three rival polities on Okinawa Island during the Sanzan period, which was eventually unified into the Ryukyu Kingdom.
  • A. Meijō
    Meijō is the Japanese name for Nagoya Castle, a historic and iconic samurai-era fortress in Nagoya, Japan.
  • B. Nanbu
    Nanbu is a town in Shizuoka Prefecture, Japan, known for its rural landscape and location near the border with Yamanashi Prefecture.
  • C. Fujinomiya
    Fujinomiya is a city in Shizuoka Prefecture, Japan, known as a major gateway to Mount Fuji and for its scenic views of the iconic volcano.
  • D. Isehara
    Isehara is a city in Kanagawa Prefecture, Japan, known as a residential and industrial area with access to nearby natural attractions such as the Tanzawa Mountains.
  • E. Higashiyamato
    Higashiyamato is a suburban city in western Tokyo, Japan, known for its residential neighborhoods and proximity to the Tama region’s parks and green spaces.
  • 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_69c008acbea48190991c6b834bb45d65 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c062547cd48190a2715537b961262e completed March 22, 2026, 9:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69c20d96415c8190b0c5c7f9fd19f5be completed March 24, 2026, 4:05 a.m.
NEDg Description generation batch_69c214980bbc8190b188b3c821ea13ea completed March 24, 2026, 4:35 a.m.
NED2 Entity disambiguation (via description) batch_69c2157d43048190a0376cdc9024c5f9 completed March 24, 2026, 4:39 a.m.
Created at: March 22, 2026, 4:20 p.m.