Triple

T24030122
Position Surface form Disambiguated ID Type / Status
Subject Princess Atsuko Ikeda E595076 entity
Predicate afterMarriageName P99359 FINISHED
Object Atsuko Ikeda
Atsuko Ikeda is a former Japanese princess, the eldest daughter of Emperor Shōwa (Hirohito), who left the imperial family upon her marriage and became known as Atsuko Ikeda.
 E1783407 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: Atsuko Ikeda | Statement: [Princess Atsuko Ikeda, afterMarriageName, Atsuko Ikeda]
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: Atsuko Ikeda
Triple: [Princess Atsuko Ikeda, afterMarriageName, Atsuko Ikeda]
Generated description
Atsuko Ikeda is a former Japanese princess, the eldest daughter of Emperor Shōwa (Hirohito), who left the imperial family upon her marriage and became known as Atsuko Ikeda.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: afterMarriageName
Context triple: [Princess Atsuko Ikeda, afterMarriageName, Atsuko Ikeda]
  • A. laterMarriedName chosen
    Indicates that the referenced name is a surname or full name a person adopted after a later marriage, replacing or succeeding their previous name.
  • B. marriedAfter
    Indicates that one marriage occurred later in time than another specified marriage.
  • C. hasMarriedSurname
    Indicates that a person’s current surname is the one they adopted through marriage.
  • D. spouseLaterMarriedBy
    Indicates that one’s spouse subsequently entered into a later marriage with another partner.
  • E. spouseNameAtMarriage
    Indicates the full name a person’s spouse had at the time of their marriage.
  • 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_69e288bf45f08190a1b6ed8cd0b9e86b completed April 17, 2026, 7:23 p.m.
NER Named-entity recognition batch_69f1d76fbedc8190a2f936729cb69993 completed April 29, 2026, 10:03 a.m.
NED1 Entity disambiguation (via context triple) batch_6a12da59d238819092bc4602e5ed6d0d completed May 24, 2026, 11 a.m.
NEDg Description generation batch_6a12daf3e7948190bb82f9eac6800971 completed May 24, 2026, 11:03 a.m.
NED2 Entity disambiguation (via description) batch_6a12db74542081909ede3d27600fb26b completed May 24, 2026, 11:05 a.m.
PD Predicate disambiguation batch_69f1764345388190a3102b62ddb729b4 completed April 29, 2026, 3:08 a.m.
Created at: April 17, 2026, 9:55 p.m.