Triple

T32424573
Position Surface form Disambiguated ID Type / Status
Subject 三井寺 E828543 entity
Predicate 開山 P174062 FINISHED
Object 智証大師円珍
智証大師円珍は、平安時代の天台宗の高僧で、入唐求法によって密教を深く学び、日本天台密教の発展に大きく貢献した人物である。
 E2006021 NE FINISHED

How this triple was built (3 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: 智証大師円珍 | Statement: [三井寺, 開山, 智証大師円珍]
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: 智証大師円珍
Triple: [三井寺, 開山, 智証大師円珍]
Generated description
智証大師円珍は、平安時代の天台宗の高僧で、入唐求法によって密教を深く学び、日本天台密教の発展に大きく貢献した人物である。
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: 開山
Context triple: [三井寺, 開山, 智証大師円珍]
  • A. 開基
    Indicates the act of founding or establishing something for the first time, such as initiating a lineage, enterprise, or domain.
  • B. 連峰
    Indicates that multiple mountain peaks are connected in a continuous range or chain.
  • C. 築城者
    Indicates the agent or person responsible for constructing or building a castle or fortress.
  • D. 本山
    Indicates a relationship or action involving "Benshan," but the predicate alone is too ambiguous to determine a specific relational meaning without additional context.
  • E. 最終階級
    Indicates the final or highest rank/grade an entity ultimately attains in a hierarchical system.
  • F. None of above. chosen

Provenance (7 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_69f3491b28bc8190b75cea7a507f337b completed April 30, 2026, 12:20 p.m.
NER Named-entity recognition batch_69f6c286ac288190843dac21651babd0 completed May 3, 2026, 3:35 a.m.
NED1 Entity disambiguation (via context triple) batch_6a344f28cc3c8190894ce0c64aca697d completed June 18, 2026, 8:03 p.m.
NEDg Description generation batch_6a344ff6fd188190b5c585e81427a37b completed June 18, 2026, 8:07 p.m.
NED2 Entity disambiguation (via description) batch_6a3450d7fb488190b39c09e0761cb81c completed June 18, 2026, 8:11 p.m.
PD Predicate disambiguation batch_69f6ba6eb32c8190bf405b2011fa48f7 completed May 3, 2026, 3:01 a.m.
PDg Predicate description generation batch_69f6bb344bb48190a8089f29c0063ded completed May 3, 2026, 3:04 a.m.
Created at: May 1, 2026, 12:54 a.m.