Triple

T21672550
Position Surface form Disambiguated ID Type / Status
Subject President of South Korea E534884 entity
Predicate style P87 FINISHED
Object Mr. President
"Mr. President" is the formal style of address used for the head of state and government of South Korea.
E1495965 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: Mr. President | Statement: [President of South Korea, style, Mr. President]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mr. President
Context triple: [President of South Korea, style, Mr. President]
  • A. Mr. President
    "Mr. President" is the formal spoken address traditionally used for the sitting President of the United States.
  • B. Mr. President
    "Mr. President" is the formal style of address used for the presiding officer of the Massachusetts Senate.
  • C. Mr. President
    "Mr. President" is the formal style of address used for the head of state of Austria.
  • D. Mr. President
    "Mr. President" is the formal style of address used for the presiding officer of the Chamber of Deputies.
  • E. Mr. President
    Mr. President is the formal style of address used for the head of state of Algeria.
  • 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: Mr. President
Triple: [President of South Korea, style, Mr. President]
Generated description
"Mr. President" is the formal style of address used for the head of state and government of South Korea.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mr. President
Target entity description: "Mr. President" is the formal style of address used for the head of state and government of South Korea.
  • A. Mr. President
    "Mr. President" is the formal style of address used for the head of state of the Russian Federation.
  • B. Mr. President
    "Mr. President" is the formal style of address used for the head of state of Romania.
  • C. Mr. President
    "Mr. President" is the formal style of address used when speaking to or about the President of the Senate of the Republic.
  • D. Mr. President
    "Mr. President" is the formal spoken address traditionally used for the sitting President of the United States.
  • E. Mr. President
    "Mr. President" is a formal style of address used for the President of Ecuador.
  • 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_69e0c46898008190aa618a4af55bd1ee completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ef8a0cd7648190b9981393f0b2bee9 completed April 27, 2026, 4:08 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0a15a7a19c8190a38ef90422f7feeb completed May 17, 2026, 7:23 p.m.
NEDg Description generation batch_6a0a16ac5ee881909ede61c149be61fa completed May 17, 2026, 7:27 p.m.
NED2 Entity disambiguation (via description) batch_6a0a17d9a48881908d9858e40d41674c completed May 17, 2026, 7:32 p.m.
Created at: April 16, 2026, 6:40 p.m.