Triple

T25227151
Position Surface form Disambiguated ID Type / Status
Subject Nagato Province E632115 entity
Predicate hasRegionCodeInGokishichidō P3446 FINISHED
Object San'yōdō
San'yōdō was one of the ancient Japanese administrative and geographic regions (and the main road running through it) along the southern coast of Honshū, encompassing several provinces facing the Seto Inland Sea.
 E1671533 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: San'yōdō | Statement: [Nagato Province, hasRegionCodeInGokishichidō, San'yōdō]
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: San'yōdō
Triple: [Nagato Province, hasRegionCodeInGokishichidō, San'yōdō]
Generated description
San'yōdō was one of the ancient Japanese administrative and geographic regions (and the main road running through it) along the southern coast of Honshū, encompassing several provinces facing the Seto Inland Sea.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: hasRegionCodeInGokishichidō
Context triple: [Nagato Province, hasRegionCodeInGokishichidō, San'yōdō]
  • A. regionOfJapan
    Indicates that one entity is a geographic region that is part of, or located within, Japan.
  • B. hasPrefecturalCode
    Indicates that an entity is associated with a specific prefectural identification code assigned by an administrative system.
  • C. hasRegionCode chosen
    Indicates that an entity is associated with a specific regional identifier or code.
  • D. locatedInRegionOfPrefecture
    Indicates that one entity is geographically situated within a specific region that belongs to or is administered as part of a given prefecture.
  • E. isPrefecture
    Indicates that one entity functions as an administrative prefecture governing or representing the other entity.
  • F. None of above.

Provenance (6 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_69e75a8e0f688190a7aebe9a4815e25b completed April 21, 2026, 11:07 a.m.
NER Named-entity recognition batch_69f72921cf2c8190909bb53f78bcc890 completed May 3, 2026, 10:53 a.m.
NED1 Entity disambiguation (via context triple) batch_6a1067da80bc8190bc2b6067a6042139 completed May 22, 2026, 2:27 p.m.
NEDg Description generation batch_6a1069760058819089d45fe0d4f630b8 completed May 22, 2026, 2:34 p.m.
NED2 Entity disambiguation (via description) batch_6a106a12f4e08190a51c4cecf7a5de2a completed May 22, 2026, 2:37 p.m.
PD Predicate disambiguation batch_69f7283d8cec8190b524c144948bc4ec completed May 3, 2026, 10:49 a.m.
Created at: April 21, 2026, 1:04 p.m.