Triple

T15442790
Position Surface form Disambiguated ID Type / Status
Subject Princess Bibesco E369947 entity
Predicate givenName P17 FINISHED
Object Elizabeth
Elizabeth is the given name of Princess Bibesco, a Romanian-British writer and socialite active in the early 20th century.
E1157442 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: Elizabeth | Statement: [Princess Bibesco, givenName, Elizabeth]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Elizabeth
Context triple: [Princess Bibesco, givenName, Elizabeth]
  • A. Elizabeth
    Elizabeth is the formal first name of Bess Truman, who served as First Lady of the United States as the wife of President Harry S. Truman.
  • B. Elizabeth
    Elizabeth was the Duchess of York who later became Queen Elizabeth The Queen Mother, a prominent member of the British royal family in the 20th century.
  • C. Elizabeth
    Elizabeth is the given name of Elizabeth Jane Cochrane, better known as pioneering American investigative journalist Nellie Bly.
  • D. Elizabeth
    Elizabeth of Denmark was a 16th-century Danish princess who became Electress of Brandenburg through her marriage to Joachim II Hector.
  • E. Elizabeth
    Elizabeth is the given first name of American actress Bess Armstrong, known for her work in film and television since the late 1970s.
  • 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: Elizabeth
Triple: [Princess Bibesco, givenName, Elizabeth]
Generated description
Elizabeth is the given name of Princess Bibesco, a Romanian-British writer and socialite active in the early 20th century.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Elizabeth
Target entity description: Elizabeth is the given name of Princess Bibesco, a Romanian-British writer and socialite active in the early 20th century.
  • A. Elizabeth
    Elizabeth is the given name of Princess Elizabeth of Yugoslavia, a Yugoslav royal and public figure.
  • B. Elizabeth
    Elizabeth is the middle name of Princess Beatrice of York, a member of the British royal family.
  • C. Elizabeth
    Elizabeth was a Greek and Danish princess of the early 20th century, born into the royal families of both Greece and Denmark.
  • D. Elizabeth
    Elizabeth is the given name of the renowned Victorian-era English poet Elizabeth Barrett Browning.
  • E. Elizabeth
    Elizabeth is the given name of Lady Elizabeth Spencer-Churchill, a member of the prominent Spencer-Churchill aristocratic family in Britain.
  • 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_69d85a19180081909925012fbf4e62a3 completed April 10, 2026, 2:02 a.m.
NER Named-entity recognition batch_69e03ef55f5c8190a32b1b6ad1daf454 completed April 16, 2026, 1:44 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff21a3d1f481908f6795656514b2b4 completed May 9, 2026, 11:59 a.m.
NEDg Description generation batch_69ff2299ac9481909ad213ff5bb01db3 completed May 9, 2026, 12:03 p.m.
NED2 Entity disambiguation (via description) batch_69ff2325e6a48190bee256ef8720ba8e completed May 9, 2026, 12:05 p.m.
Created at: April 10, 2026, 3:21 a.m.