Triple

T1778822
Position Surface form Disambiguated ID Type / Status
Subject Albert I of Belgium E39241 entity
Predicate mother P120 FINISHED
Object Princess Marie of Hohenzollern-Sigmaringen
Princess Marie of Hohenzollern-Sigmaringen was a 19th-century German princess of the Hohenzollern-Sigmaringen dynasty who became Queen of the Belgians as the wife of King Leopold II and the mother of King Albert I.
E311337 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: Princess Marie of Hohenzollern-Sigmaringen | Statement: [Albert I of Belgium, mother, Princess Marie of Hohenzollern-Sigmaringen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Princess Marie of Hohenzollern-Sigmaringen
Context triple: [Albert I of Belgium, mother, Princess Marie of Hohenzollern-Sigmaringen]
  • A. Princess Marie of Hesse and by Rhine
    Princess Marie of Hesse and by Rhine was a German princess of the House of Hesse and by Rhine, a granddaughter of Queen Victoria who died in childhood from diphtheria.
  • B. Princess Irene of Hesse and by Rhine
    Princess Irene of Hesse and by Rhine was a German princess, granddaughter of Queen Victoria, and wife of Prince Heinrich of Prussia, known for her close ties to several European royal families.
  • C. Princess Marie von Thurn und Taxis
    Princess Marie von Thurn und Taxis was an aristocratic patron of the arts best known for her close friendship and extensive correspondence with poet Rainer Maria Rilke, whom she supported creatively and financially.
  • D. Sophia Louise of Mecklenburg-Schwerin
    Sophia Louise of Mecklenburg-Schwerin was a German duchess who became Queen consort in Prussia through her marriage into the Hohenzollern dynasty in the early 18th century.
  • E. Princess Marie Astrid of Luxembourg
    Princess Marie Astrid of Luxembourg is a member of the Grand Ducal Family of Luxembourg and the eldest daughter of Grand Duke Jean and Grand Duchess Joséphine-Charlotte.
  • 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: Princess Marie of Hohenzollern-Sigmaringen
Triple: [Albert I of Belgium, mother, Princess Marie of Hohenzollern-Sigmaringen]
Generated description
Princess Marie of Hohenzollern-Sigmaringen was a 19th-century German princess of the Hohenzollern-Sigmaringen dynasty who became Queen of the Belgians as the wife of King Leopold II and the mother of King Albert I.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Princess Marie of Hohenzollern-Sigmaringen
Target entity description: Princess Marie of Hohenzollern-Sigmaringen was a 19th-century German princess of the Hohenzollern-Sigmaringen dynasty who became Queen of the Belgians as the wife of King Leopold II and the mother of King Albert I.
  • A. Princess Marie of Hesse and by Rhine
    Princess Marie of Hesse and by Rhine was a German princess of the House of Hesse and by Rhine, a granddaughter of Queen Victoria who died in childhood from diphtheria.
  • B. Princess Irene of Hesse and by Rhine
    Princess Irene of Hesse and by Rhine was a German princess, granddaughter of Queen Victoria, and wife of Prince Heinrich of Prussia, known for her close ties to several European royal families.
  • C. Princess Marie von Thurn und Taxis
    Princess Marie von Thurn und Taxis was an aristocratic patron of the arts best known for her close friendship and extensive correspondence with poet Rainer Maria Rilke, whom she supported creatively and financially.
  • D. Sophia Louise of Mecklenburg-Schwerin
    Sophia Louise of Mecklenburg-Schwerin was a German duchess who became Queen consort in Prussia through her marriage into the Hohenzollern dynasty in the early 18th century.
  • E. Princess Marie Astrid of Luxembourg
    Princess Marie Astrid of Luxembourg is a member of the Grand Ducal Family of Luxembourg and the eldest daughter of Grand Duke Jean and Grand Duchess Joséphine-Charlotte.
  • 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_69a88630519c8190a17addd83c4a3ef4 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa64ba92a48190b69da748dfbfc53c completed March 6, 2026, 5:23 a.m.
NED1 Entity disambiguation (via context triple) batch_69b085fc357481908259683cb4860cf3 completed March 10, 2026, 8:58 p.m.
NEDg Description generation batch_69b0d499cf108190beee4b64d88e9f3d completed March 11, 2026, 2:34 a.m.
NED2 Entity disambiguation (via description) batch_69b0d4fbdc7481909307e569b1874fe0 completed March 11, 2026, 2:35 a.m.
Created at: March 4, 2026, 7:31 p.m.