Triple

T11719023
Position Surface form Disambiguated ID Type / Status
Subject John I, Duke of Brittany E278577 entity
Predicate givenName P17 FINISHED
Object John
John I, Duke of Brittany, was a 13th-century French nobleman who ruled Brittany and was involved in the complex feudal politics between France and England.
E943384 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: John | Statement: [John I, Duke of Brittany, givenName, John]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John
Context triple: [John I, Duke of Brittany, givenName, John]
  • A. John
    John is the given first name of Johnny Kilbane, an American featherweight boxing champion from the early 20th century.
  • B. John
    John is the middle name of Samuel John Mills, an American Congregationalist minister known for his role in early 19th-century missionary movements.
  • C. John
    John is the given first name of the 19th-century English theologian and social reformer Frederick Denison Maurice.
  • D. John
    John is the given name of John Eales, the renowned former Australian rugby union captain and World Cup winner.
  • E. John
    John is the common given name of American author and YouTube creator John Green, known for novels like "The Fault in Our Stars" and for co-founding the Vlogbrothers channel.
  • 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: John
Triple: [John I, Duke of Brittany, givenName, John]
Generated description
John I, Duke of Brittany, was a 13th-century French nobleman who ruled Brittany and was involved in the complex feudal politics between France and England.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: John
Target entity description: John I, Duke of Brittany, was a 13th-century French nobleman who ruled Brittany and was involved in the complex feudal politics between France and England.
  • A. John
    John of Montfort was a 14th-century nobleman involved in the Breton succession disputes during the Hundred Years’ War.
  • B. John
    John the Fearless was a powerful early 15th-century Duke of Burgundy known for his aggressive political maneuvers and pivotal role in the French civil conflicts of the Hundred Years’ War.
  • C. John
    John II of France was a 14th-century King of France, known as "John the Good," whose reign was marked by the Hundred Years' War and his capture at the Battle of Poitiers.
  • D. John
    John was a medieval English monarch who ruled as King John of England from 1199 to 1216 and is best known for sealing the Magna Carta.
  • E. John
    John is the given name of Sir John Woodville, a 15th-century English nobleman associated with the influential Woodville family during the Wars of the Roses.
  • 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_69d6aaff2ce88190b4a1e4b341ad5377 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a4c26e4c8190ae30d906b4fd4221 completed April 10, 2026, 7:20 a.m.
NED1 Entity disambiguation (via context triple) batch_69f0196916e081908671e79765d03778 completed April 28, 2026, 2:20 a.m.
NEDg Description generation batch_69f0319271788190a105828ae7582668 completed April 28, 2026, 4:03 a.m.
NED2 Entity disambiguation (via description) batch_69f05a44dcb88190a0bb57b0c8fef6b9 completed April 28, 2026, 6:57 a.m.
Created at: April 8, 2026, 9:40 p.m.