Triple

T2288203
Position Surface form Disambiguated ID Type / Status
Subject Yoo Soon-taek E51441 entity
Predicate honorificTitle P2097 FINISHED
Object Madame Ban
Madame Ban is the honorific title commonly used for Yoo Soon-taek, the wife of former United Nations Secretary-General Ban Ki-moon and a prominent South Korean public figure.
E253074 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: Madame Ban | Statement: [Yoo Soon-taek, honorificTitle, Madame Ban]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Madame Ban
Context triple: [Yoo Soon-taek, honorificTitle, Madame Ban]
  • A. Blanchette
    Blanchette is a French feminine given name and diminutive form of Blanche, traditionally meaning "white" or "fair."
  • B. Barbara
    Barbara is a station on Paris Métro Line 4 serving the southern suburbs of the French capital.
  • C. Barbara
    Barbara is a feminine given name of Greek origin that has been widely used in many cultures and languages.
  • D. Madame Leota
    Madame Leota is a disembodied, ghostly medium whose talking head in a crystal ball delivers eerie incantations in Disney’s Haunted Mansion attraction.
  • E. Mabel Grex
    Mabel Grex is a central fictional character in Anthony Trollope’s novel "The Duke's Children," known for her beauty, charm, and complex romantic entanglements within high society.
  • 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: Madame Ban
Triple: [Yoo Soon-taek, honorificTitle, Madame Ban]
Generated description
Madame Ban is the honorific title commonly used for Yoo Soon-taek, the wife of former United Nations Secretary-General Ban Ki-moon and a prominent South Korean public figure.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Madame Ban
Target entity description: Madame Ban is the honorific title commonly used for Yoo Soon-taek, the wife of former United Nations Secretary-General Ban Ki-moon and a prominent South Korean public figure.
  • A. Blanchette
    Blanchette is a French feminine given name and diminutive form of Blanche, traditionally meaning "white" or "fair."
  • B. Barbara
    Barbara is a station on Paris Métro Line 4 serving the southern suburbs of the French capital.
  • C. Barbara
    Barbara is a feminine given name of Greek origin that has been widely used in many cultures and languages.
  • D. Madame Leota
    Madame Leota is a disembodied, ghostly medium whose talking head in a crystal ball delivers eerie incantations in Disney’s Haunted Mansion attraction.
  • E. Mabel Grex
    Mabel Grex is a central fictional character in Anthony Trollope’s novel "The Duke's Children," known for her beauty, charm, and complex romantic entanglements within high society.
  • 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_69a88b09c644819090b503456d96bf70 completed March 4, 2026, 7:42 p.m.
NER Named-entity recognition batch_69abc2497ce881909b05eb9cec67d9e7 completed March 7, 2026, 6:14 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae7f1b2a7c8190aa836f9feba2ce1a completed March 9, 2026, 8:04 a.m.
NEDg Description generation batch_69ae8004fb6c81908f9fb1678f608419 completed March 9, 2026, 8:08 a.m.
NED2 Entity disambiguation (via description) batch_69ae809ebfdc8190ae404d5711a58b59 completed March 9, 2026, 8:11 a.m.
Created at: March 4, 2026, 7:48 p.m.