Triple

T14928892
Position Surface form Disambiguated ID Type / Status
Subject Duke Carl of Württemberg E372205 entity
Predicate givenName P17 FINISHED
Object Carl
Carl is a member of the royal House of Württemberg, known as Duke Carl of Württemberg in the German nobility.
E1127340 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: Carl | Statement: [Duke Carl of Württemberg, givenName, Carl]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Carl
Context triple: [Duke Carl of Württemberg, givenName, Carl]
  • A. Carl
    Carl is the given name of Carl Sagan, the renowned American astronomer, science communicator, and author.
  • B. Carl
    Carl is the given name of the influential American microbiologist Carl Woese, known for defining the Archaea domain of life.
  • C. Carl
    Carl is the given name of Carl Schorske, a prominent American cultural and intellectual historian known for his influential work on fin-de-siècle Vienna.
  • D. Carl
    Carl is the given name of the German Romantic composer and conductor Carl Maria von Weber, known for works such as the opera "Der Freischütz."
  • E. Carl
    Carl is a supporting character in the film "Van Helsing," depicted as a witty and inventive friar who aids the titular monster hunter.
  • 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: Carl
Triple: [Duke Carl of Württemberg, givenName, Carl]
Generated description
Carl is a member of the royal House of Württemberg, known as Duke Carl of Württemberg in the German nobility.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Carl
Target entity description: Carl is a member of the royal House of Württemberg, known as Duke Carl of Württemberg in the German nobility.
  • A. Carl
    Carl is the given name of Charles Frederick, Duke of Holstein-Gottorp, an 18th-century German prince linked to the Russian imperial family.
  • B. Carl
    Carl is the given name of Charles III William, the Margrave of Baden-Durlach, a German nobleman and regional ruler of the early 18th century.
  • C. Carl
    Carl is the given name of Charles I Louis, the 17th-century Elector Palatine of the Rhine in the Holy Roman Empire.
  • D. Carl
    Carl is a masculine given name of Germanic origin that is related to Charles and commonly used in many English-speaking and European countries.
  • E. Carl
    Carl is the given name of Carl Philipp Emanuel Bach, an influential 18th-century German composer and musician of the Classical period.
  • 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_69d85cc9da0c81908d583ca3f63a3908 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded634e67881909daec9eaef188d09 completed April 15, 2026, 12:05 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe72c4f9c481909642efccb29f71d4 completed May 8, 2026, 11:33 p.m.
NEDg Description generation batch_69fe744b9c048190ae2a64da53d8ffac completed May 8, 2026, 11:39 p.m.
NED2 Entity disambiguation (via description) batch_69fe74d510808190a2379a2380fc327e completed May 8, 2026, 11:42 p.m.
Created at: April 10, 2026, 2:36 a.m.