Triple

T23338364
Position Surface form Disambiguated ID Type / Status
Subject Princess Takako Shimazu E591661 entity
Predicate titleBeforeMarriage P53189 FINISHED
Object Her Imperial Highness Princess Takako
Her Imperial Highness Princess Takako is a member of the Japanese Imperial Family, the fifth daughter of Emperor Shōwa (Hirohito) and Empress Kōjun, who became Princess Takako Shimazu upon her marriage.
 E1592348 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: Her Imperial Highness Princess Takako | Statement: [Princess Takako Shimazu, titleBeforeMarriage, Her Imperial Highness Princess Takako]
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: Her Imperial Highness Princess Takako
Triple: [Princess Takako Shimazu, titleBeforeMarriage, Her Imperial Highness Princess Takako]
Generated description
Her Imperial Highness Princess Takako is a member of the Japanese Imperial Family, the fifth daughter of Emperor Shōwa (Hirohito) and Empress Kōjun, who became Princess Takako Shimazu upon her marriage.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: titleBeforeMarriage
Context triple: [Princess Takako Shimazu, titleBeforeMarriage, Her Imperial Highness Princess Takako]
  • A. aristocraticTitleBeforeMarriage chosen
    Indicates that the subject held a specific aristocratic title prior to entering into marriage.
  • B. titleFromSpouse
    Indicates that an entity holds a title or honorific that is derived from or acquired through their spouse.
  • C. styleBeforeMarriage
    Indicates that the referenced style or appearance pertains to an individual’s state prior to their marriage.
  • D. marriageBefore
    Indicates that one marriage event occurred earlier in time than another marriage event.
  • E. partnerBeforeMarriage
    Indicates that one entity was the romantic or life partner of another entity prior to 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_69e25d20156c81908c5c53195bd9c738 completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f1983099188190a2e05cf81d62a641 completed April 29, 2026, 5:33 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0f4541bb30819089b3793aaf949f93 completed May 21, 2026, 5:47 p.m.
NEDg Description generation batch_6a0f461940e4819083efc41c455897e7 completed May 21, 2026, 5:51 p.m.
NED2 Entity disambiguation (via description) batch_6a0f469597788190afac9f7b9868ee97 completed May 21, 2026, 5:53 p.m.
PD Predicate disambiguation batch_69effcfd8d288190937a887fe6023c11 completed April 28, 2026, 12:19 a.m.
Created at: April 17, 2026, 5:17 p.m.