Triple

T16365520
Position Surface form Disambiguated ID Type / Status
Subject Princess Alexandra of Greece and Denmark E397426 entity
Predicate patronymicName P7966 FINISHED
Object Georgievna
Georgievna is the Russian-style patronymic indicating that Princess Alexandra of Greece and Denmark was the daughter of King George.
 E1208527 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: Georgievna | Statement: [Princess Alexandra of Greece and Denmark, patronymicName, Georgievna]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Georgievna
Context triple: [Princess Alexandra of Greece and Denmark, patronymicName, Georgievna]
  • A. Grigoryevna
    Grigoryevna is a Russian female patronymic indicating that a person is the daughter of someone named Grigory.
  • B. Borisovna
    Borisovna is a Russian patronymic given name indicating that a woman is the daughter of someone named Boris.
  • C. Evgenia
    Evgenia is a feminine given name commonly used in Slavic and Greek cultures, derived from the Greek name Eugenia meaning "well-born" or "noble."
  • D. Sergeyevna
    Sergeyevna is a Russian female patronymic indicating that a woman is the daughter of a man named Sergei.
  • E. Eudoxia Streshneva
    Eudoxia Streshneva was a 17th-century Russian tsarina and the second wife of Tsar Michael I, noted as the mother of Tsar Alexis of Russia.
  • 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: Georgievna
Triple: [Princess Alexandra of Greece and Denmark, patronymicName, Georgievna]
Generated description
Georgievna is the Russian-style patronymic indicating that Princess Alexandra of Greece and Denmark was the daughter of King George.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Georgievna
Target entity description: Georgievna is the Russian-style patronymic indicating that Princess Alexandra of Greece and Denmark was the daughter of King George.
  • A. Grigoryevna
    Grigoryevna is a Russian female patronymic indicating that a person is the daughter of someone named Grigory.
  • B. Borisovna
    Borisovna is a Russian patronymic given name indicating that a woman is the daughter of someone named Boris.
  • C. Evgenia
    Evgenia is a feminine given name commonly used in Slavic and Greek cultures, derived from the Greek name Eugenia meaning "well-born" or "noble."
  • D. Sergeyevna
    Sergeyevna is a Russian female patronymic indicating that a woman is the daughter of a man named Sergei.
  • E. Eudoxia Streshneva
    Eudoxia Streshneva was a 17th-century Russian tsarina and the second wife of Tsar Michael I, noted as the mother of Tsar Alexis of Russia.
  • 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_69d87f2778dc8190aa95c7572db127e6 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e2ff3c915c81909e1757fc31921876 completed April 18, 2026, 3:49 a.m.
NED1 Entity disambiguation (via context triple) batch_6a002dc0b3d4819089e6fba536ec8a11 completed May 10, 2026, 7:03 a.m.
NEDg Description generation batch_6a002f35af8081908ea9c3d0a991c396 completed May 10, 2026, 7:09 a.m.
NED2 Entity disambiguation (via description) batch_6a002fa14ee4819080b02b368c0080b9 completed May 10, 2026, 7:11 a.m.
Created at: April 10, 2026, 5:08 a.m.