Triple

T6931189
Position Surface form Disambiguated ID Type / Status
Subject Daini Denden (DDI) E160436 entity
Predicate shortName P43 FINISHED
Object DDI
DDI is the abbreviated name for Daini Denden, a former Japanese telecommunications company that emerged from the privatization of Japan’s national phone services.
 E629086 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: DDI | Statement: [Daini Denden (DDI), shortName, DDI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: DDI
Context triple: [Daini Denden (DDI), shortName, DDI]
  • A. DDI
    DDI is the abbreviation for the Directorate of Digital Innovation, a CIA directorate focused on advancing the agency’s digital and cyber capabilities.
  • B. DDDN
    DDDN is a medical division specializing in the research, diagnosis, and treatment of digestive system and nutritional disorders.
  • C. DDC
    DDC is the IATA airport code for Dodge City Regional Airport, a public airport serving Dodge City in southwestern Kansas, United States.
  • D. DDC
    DDC is a widely used library classification system that organizes books and other materials into numbered subject categories for easy retrieval.
  • E. DDC
    DDC is the Dart Dev Compiler, a tool that compiles Dart code to efficient JavaScript for web development.
  • 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: DDI
Triple: [Daini Denden (DDI), shortName, DDI]
Generated description
DDI is the abbreviated name for Daini Denden, a former Japanese telecommunications company that emerged from the privatization of Japan’s national phone services.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: DDI
Target entity description: DDI is the abbreviated name for Daini Denden, a former Japanese telecommunications company that emerged from the privatization of Japan’s national phone services.
  • A. DDI
    DDI is the abbreviation for the Directorate of Digital Innovation, a CIA directorate focused on advancing the agency’s digital and cyber capabilities.
  • B. DDDN
    DDDN is a medical division specializing in the research, diagnosis, and treatment of digestive system and nutritional disorders.
  • C. DDC
    DDC is the Dart Dev Compiler, a tool that compiles Dart code to efficient JavaScript for web development.
  • D. DDC
    DDC is the IATA airport code for Dodge City Regional Airport, a public airport serving Dodge City in southwestern Kansas, United States.
  • E. DDC
    DDC is a widely used library classification system that organizes books and other materials into numbered subject categories for easy retrieval.
  • 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_69c6884e15208190b9e91487eaafcf85 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6da3e58f08190857c14f538448039 completed March 27, 2026, 7:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7514b0dd8819097a3fa1a38c913f4 completed March 28, 2026, 3:55 a.m.
NEDg Description generation batch_69c75280eaa4819089b5e76a817b1330 completed March 28, 2026, 4:01 a.m.
NED2 Entity disambiguation (via description) batch_69c75306e62c8190ba2f4db741bd1ff9 completed March 28, 2026, 4:03 a.m.
Created at: March 27, 2026, 2:27 p.m.