Triple

T19739420
Position Surface form Disambiguated ID Type / Status
Subject Louis I, Count of Clermont-en-Beauvaisis E474073 entity
Predicate givenName P17 FINISHED
Object Louis
Louis was the personal name of Louis I, Count of Clermont-en-Beauvaisis, a 13th-century French nobleman of the Capetian dynasty.
E1392665 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: Louis | Statement: [Louis I, Count of Clermont-en-Beauvaisis, givenName, Louis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Louis
Context triple: [Louis I, Count of Clermont-en-Beauvaisis, givenName, Louis]
  • A. Louis
    Louis is the family name of Spyridon Louis, the Greek runner who won the first modern Olympic marathon in 1896.
  • B. Louis
    Louis is the given name of Louis Althusser, a prominent 20th-century French Marxist philosopher known for his structuralist interpretation of Marxism.
  • C. Louis
    Louis is the given first name of Lou Piniella, a former Major League Baseball outfielder and World Series–winning manager.
  • D. Louis
    Louis is one of the central introspective narrators in Virginia Woolf’s modernist novel "The Waves," known for his outsider status and poetic, self-analytical inner life.
  • E. Louis
    Louis was the personal name of Louis I, the first Grand Duke of Hesse, a 19th-century German ruler.
  • 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: Louis
Triple: [Louis I, Count of Clermont-en-Beauvaisis, givenName, Louis]
Generated description
Louis was the personal name of Louis I, Count of Clermont-en-Beauvaisis, a 13th-century French nobleman of the Capetian dynasty.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Louis
Target entity description: Louis was the personal name of Louis I, Count of Clermont-en-Beauvaisis, a 13th-century French nobleman of the Capetian dynasty.
  • A. Louis
    Louis was the personal name of Louis I, Duke of Bourbon, a prominent 13th–14th century French nobleman and founder of the House of Bourbon.
  • B. Louis
    Louis was a French nobleman of the Bourbon-Condé line who held the title of comte de Clermont and was active in 18th-century military and court life.
  • C. Louis
    Louis was the given name of Louis II d’Orléans, Duke of Longueville, a French nobleman of the late medieval and early Renaissance period.
  • D. Louis
    Louis was the given name of Louis I, Cardinal of Guise, a prominent 16th-century French Catholic prelate and member of the influential House of Guise.
  • E. Louis
    Louis was the given name of Louis II of Chalon-Arlay, a 15th-century French nobleman and Prince of Orange.
  • 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_69d8e517ebd48190979ee76723bcfadf completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e651607e388190bbb2aaed252820fe completed April 20, 2026, 4:16 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07b4fba58c819090fdfb319096aa0a completed May 16, 2026, 12:06 a.m.
NEDg Description generation batch_6a07b670aa0481908cc918b32b512712 completed May 16, 2026, 12:12 a.m.
NED2 Entity disambiguation (via description) batch_6a07b6e4ae348190a3783c6a82059793 completed May 16, 2026, 12:14 a.m.
Created at: April 10, 2026, 1:47 p.m.