Triple

T22233501
Position Surface form Disambiguated ID Type / Status
Subject Prince Kan'in Kotohito E549527 entity
Predicate familyName P18 FINISHED
Object Kan'in
Kan'in is a Japanese princely house that formed one of the collateral branches of the Imperial Family.
 E1570591 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: Kan'in | Statement: [Prince Kan'in Kotohito, familyName, Kan'in]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kan'in
Context triple: [Prince Kan'in Kotohito, familyName, Kan'in]
  • A. Kan’onji
    Kan’onji is a coastal city in western Kagawa Prefecture on Japan’s Shikoku Island, known for its historic temples and scenic views of the Seto Inland Sea.
  • B. Kanze
    Kanze is a prominent Japanese family name historically associated with a major school of Noh theatre.
  • C. Kakunyo
    Kakunyo was a Japanese Buddhist monk of the Jōdo Shinshū tradition, known for systematizing his grandfather Shinran’s teachings and compiling early histories of the sect.
  • D. Kanmaki
    Kanmaki is a town in Nara Prefecture, Japan, known as a residential community within the Kansai region.
  • E. Nakanai
    Nakanai is an Austronesian language spoken on the island of New Britain in Papua New Guinea, known for its role in the linguistic diversity of the Bismarck Archipelago.
  • 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: Kan'in
Triple: [Prince Kan'in Kotohito, familyName, Kan'in]
Generated description
Kan'in is a Japanese princely house that formed one of the collateral branches of the Imperial Family.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kan'in
Target entity description: Kan'in is a Japanese princely house that formed one of the collateral branches of the Imperial Family.
  • A. Kan’onji
    Kan’onji is a coastal city in western Kagawa Prefecture on Japan’s Shikoku Island, known for its historic temples and scenic views of the Seto Inland Sea.
  • B. Kanze
    Kanze is a prominent Japanese family name historically associated with a major school of Noh theatre.
  • C. Kakunyo
    Kakunyo was a Japanese Buddhist monk of the Jōdo Shinshū tradition, known for systematizing his grandfather Shinran’s teachings and compiling early histories of the sect.
  • D. Kanmaki
    Kanmaki is a town in Nara Prefecture, Japan, known as a residential community within the Kansai region.
  • E. Nakanai
    Nakanai is an Austronesian language spoken on the island of New Britain in Papua New Guinea, known for its role in the linguistic diversity of the Bismarck Archipelago.
  • 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_69e11e4102b881909cf47d3768e25c19 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f12bf4e0348190b755a9ac0bc96cdd completed April 28, 2026, 9:51 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0c23cb8d4c8190a9734373347ab25f completed May 19, 2026, 8:48 a.m.
NEDg Description generation batch_6a0c272d23a881909da657509f51cd71 completed May 19, 2026, 9:02 a.m.
NED2 Entity disambiguation (via description) batch_6a0c27aa2ce0819097ed29d8b89aef6e completed May 19, 2026, 9:04 a.m.
Created at: April 16, 2026, 8:38 p.m.