Triple

T13620630
Position Surface form Disambiguated ID Type / Status
Subject Elizabeth of Denmark E325440 entity
Predicate givenName P17 FINISHED
Object Elizabeth
Elizabeth of Denmark was a 16th-century Danish princess who became Electress of Brandenburg through her marriage to Joachim II Hector.
E1050659 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: [Elizabeth of Denmark, givenName, Elizabeth]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Elizabeth
Context triple: [Elizabeth of Denmark, givenName, Elizabeth]
  • A. Elizabeth
    Elizabeth "Betty" Ford was the influential First Lady of the United States from 1974 to 1977, renowned for her advocacy on women's rights, breast cancer awareness, and addiction treatment.
  • B. Elizabeth
    Elizabeth is the middle name of Diane Elizabeth Dern, an individual likely known in relation to the Dern family.
  • C. Elizabeth
    Elizabeth is an alternate given name associated with Mary Surratt, the American boardinghouse owner convicted and executed for her role in the conspiracy to assassinate President Abraham Lincoln.
  • D. Elizabeth
    Elizabeth is the middle name of Princess Beatrice of York, a member of the British royal family.
  • E. Elizabeth
    Elizabeth is the full given name of Betsy McCaughey, an American politician, writer, and former lieutenant governor of New York.
  • 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: [Elizabeth of Denmark, givenName, Elizabeth]
Generated description
Elizabeth of Denmark was a 16th-century Danish princess who became Electress of Brandenburg through her marriage to Joachim II Hector.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Elizabeth
Target entity description: Elizabeth of Denmark was a 16th-century Danish princess who became Electress of Brandenburg through her marriage to Joachim II Hector.
  • A. Elizabeth
    Elizabeth was a Greek and Danish princess of the early 20th century, born into the royal families of both Greece and Denmark.
  • B. Elizabeth
    Elizabeth was a German noblewoman who held the title of Landgravine of Hesse-Homburg.
  • C. Elizabeth
    Elizabeth was a medieval English noblewoman, the daughter of John of Gaunt and granddaughter of King Edward III.
  • D. Elizabeth
    Elizabeth of Rhuddlan was an English princess, the youngest daughter of King Edward I of England and Eleanor of Castile, known for her politically significant marriages into the nobility of Holland and Hereford.
  • E. Elizabeth
    Elizabeth of Bohemia was a 17th-century princess and philosopher known for her extensive correspondence with René Descartes and her influential critiques of his dualism.
  • 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_69d8076aae28819092cf636190ee5529 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbb0b0c9008190836242da2d6a8cbe completed April 12, 2026, 2:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69f77f7fcab0819091146d54d56f08d7 completed May 3, 2026, 5:01 p.m.
NEDg Description generation batch_69f78125632881908d601ee4c4aaae35 completed May 3, 2026, 5:08 p.m.
NED2 Entity disambiguation (via description) batch_69f781e32cb48190abc83e65405ac8ac completed May 3, 2026, 5:12 p.m.
Created at: April 9, 2026, 9:50 p.m.