Triple

T14151192
Position Surface form Disambiguated ID Type / Status
Subject Princess Mary of the United Kingdom E350682 entity
Predicate givenName P17 FINISHED
Object Mary
Mary was a British princess, the only daughter of King George V and Queen Mary, and a member of the House of Windsor in the early 20th century.
E21175 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: Mary | Statement: [Princess Mary of the United Kingdom, givenName, Mary]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary
Context triple: [Princess Mary of the United Kingdom, givenName, Mary]
  • A. Mary
    Mary is the given first name of the acclaimed American actress Meryl Streep.
  • B. Mary
    Mary is the given name of Mary Everest Boole, a 19th-century mathematics educator known for her innovative ideas on teaching mathematics, especially to children.
  • C. Mary
    "Mary" is a 1949 novel by Polish-Jewish writer Sholem Asch that reimagines the life of Jesus through the perspective of his mother.
  • D. Mary
    Mary of Waltham, Duchess of Brittany, was a 14th-century English princess and daughter of King Edward III who became duchess through her marriage to John IV, Duke of Brittany.
  • E. Mary
    Mary of Guelders was a 15th-century duchess who became Queen consort of Scotland as the wife of King James II.
  • 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: Mary
Triple: [Princess Mary of the United Kingdom, givenName, Mary]
Generated description
Mary was a British princess, the only daughter of King George V and Queen Mary, and a member of the House of Windsor in the early 20th century.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mary
Target entity description: Mary was a British princess, the only daughter of King George V and Queen Mary, and a member of the House of Windsor in the early 20th century.
  • A. Mary chosen
    Mary, Princess Royal and Countess of Harewood, was a daughter of King George V and Queen Mary of the United Kingdom and a prominent British royal figure in the early to mid-20th century.
  • B. Mary
    Mary, Princess Royal and Princess of Orange, was the eldest daughter of King Charles I of England and the wife of William II of Orange, making her a key figure in 17th-century Anglo-Dutch royal relations.
  • C. Mary
    Mary is one of the middle names of Princess Beatrice of York, a member of the British royal family.
  • D. Mary
    Mary is the eldest daughter of the Crawley family and a central character in the British period drama series "Downton Abbey."
  • E. Mary
    Mary of York was a 15th-century English princess, the second daughter of King Edward IV and Elizabeth Woodville.
  • F. None of above.

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_69d8278775fc8190b0802d22ca2f495d completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de6124e23481909e5132a40a1d8624 completed April 14, 2026, 3:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcdf21f8c8819097ff26e6bb345b52 completed May 7, 2026, 6:51 p.m.
NEDg Description generation batch_69fce0cc78e881909090ac42a97ebb12 completed May 7, 2026, 6:58 p.m.
NED2 Entity disambiguation (via description) batch_69fce1f53a8881909fd1258729a9879d completed May 7, 2026, 7:03 p.m.
Created at: April 10, 2026, 12:57 a.m.