Triple

T17868280
Position Surface form Disambiguated ID Type / Status
Subject Carol I of Romania E446762 entity
Predicate givenName P17 FINISHED
Object Karl
Karl is the birth name of Carol I of Romania, the 19th-century Prussian prince who became Romania’s first king and a key figure in its modernization and independence.
E873815 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: Karl | Statement: [Carol I of Romania, givenName, Karl]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Karl
Context triple: [Carol I of Romania, givenName, Karl]
  • A. Karl
    Karl is the given first name of Charles Proteus Steinmetz, the renowned German-American mathematician and electrical engineer who revolutionized the understanding of alternating current systems.
  • B. Karl
    Karl is a ruthless, long-haired German terrorist and Hans Gruber’s vengeful right-hand man in the action film "Die Hard."
  • C. Karl
    Karl was the given name of Archduke Charles Joseph of Austria, a Habsburg archduke and younger brother of Empress Maria Theresa in the 18th century.
  • D. Karl
    Karl is the given name of Karl Malone, the Hall of Fame NBA power forward best known for his long career with the Utah Jazz.
  • E. Karl
    Karl Ferdinand of Bavaria was a Bavarian prince from the royal House of Wittelsbach in the late 19th and early 20th centuries.
  • 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: Karl
Triple: [Carol I of Romania, givenName, Karl]
Generated description
Karl is the birth name of Carol I of Romania, the 19th-century Prussian prince who became Romania’s first king and a key figure in its modernization and independence.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Karl
Target entity description: Karl is the birth name of Carol I of Romania, the 19th-century Prussian prince who became Romania’s first king and a key figure in its modernization and independence.
  • A. Karl chosen
    Karl is the given first name of Carol I of Romania, the 19th-century Prussian-born prince who became the first king of modern Romania.
  • B. Karl
    Karl is the given name of Prince Karl von Lichnowsky, a notable German aristocrat and diplomat of the early 20th century.
  • C. Karl
    Karl is the given name of Charles Frederick, the Grand Duke of Baden, a prominent German ruler of the late 18th and early 19th centuries.
  • D. Karl
    Karl was the given name of Prince Louis Charles of Prussia, a member of the Prussian royal family in the late 18th and early 19th centuries.
  • E. Karl
    Karl is a given name borne by Prince Friedrich Heinrich Emil Karl of Prussia, a member of the Prussian royal family.
  • 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_69d8b9f4c22c819093c2680434472894 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e49aa0b69081909fba3b42d237b543 completed April 19, 2026, 9:04 a.m.
NED1 Entity disambiguation (via context triple) batch_6a030c5e368081908df3a20cd40aeb9f completed May 12, 2026, 11:17 a.m.
NEDg Description generation batch_6a030d2ebb44819083c58cfae6c7ca47 completed May 12, 2026, 11:21 a.m.
NED2 Entity disambiguation (via description) batch_6a030e1b78388190bbad5f4f967c31d3 completed May 12, 2026, 11:25 a.m.
Created at: April 10, 2026, 10:17 a.m.