Triple

T22474043
Position Surface form Disambiguated ID Type / Status
Subject George of Austria E555579 entity
Predicate givenName P17 FINISHED
Object George
George of Austria was a 16th-century Habsburg prince who served as Prince-Bishop of Liège and played a notable role in the politics of the Holy Roman Empire.
E1539405 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: George | Statement: [George of Austria, givenName, George]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: George
Context triple: [George of Austria, givenName, George]
  • A. George
    George is the given name of George W. McLaurin, the first African American student admitted to the University of Oklahoma.
  • B. George
    George is the given name of Lord George Gordon, an 18th-century British politician best known for inciting the anti-Catholic Gordon Riots of 1780.
  • C. George
    George is the given name of George K. Zipf, the American linguist and philologist known for formulating Zipf's law about word frequency distributions.
  • D. George
    George is the given name of George Spencer, 4th Duke of Marlborough, an 18th-century British nobleman and politician.
  • E. George
    George is the given name of George Keith, 10th Earl Marischal, a prominent Scottish nobleman and statesman of the 17th century.
  • 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: George
Triple: [George of Austria, givenName, George]
Generated description
George of Austria was a 16th-century Habsburg prince who served as Prince-Bishop of Liège and played a notable role in the politics of the Holy Roman Empire.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: George
Target entity description: George of Austria was a 16th-century Habsburg prince who served as Prince-Bishop of Liège and played a notable role in the politics of the Holy Roman Empire.
  • A. George
    George I Rákóczi was a 17th-century Prince of Transylvania known for strengthening the principality and navigating complex political relations with the Ottoman Empire and the Habsburgs.
  • B. George
    George, Crown Prince of Serbia, is a historical royal figure who was heir apparent to the Serbian throne in the early 20th century.
  • C. George
    George was the given name of George II, Landgrave of Hesse-Darmstadt, an 18th-century German nobleman and ruler within the Holy Roman Empire.
  • D. George
    George is the given name of George II Rákóczi, a 17th-century Prince of Transylvania from the influential Rákóczi noble family.
  • E. George
    George is the given name of George Gordon, 4th Earl of Huntly, a prominent 16th-century Scottish nobleman and political figure.
  • 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_69e11e52c2048190952dc5df209b9bed completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15be2d5388190a59d11b3403d998b completed April 29, 2026, 1:16 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b125b26008190a232bac277b253c5 completed May 18, 2026, 1:21 p.m.
NEDg Description generation batch_6a0b14b7acac819090bfd6144df84be6 completed May 18, 2026, 1:31 p.m.
NED2 Entity disambiguation (via description) batch_6a0b154f7e0c8190b0ca64d582982d62 completed May 18, 2026, 1:34 p.m.
Created at: April 16, 2026, 8:49 p.m.