Triple

T12211263
Position Surface form Disambiguated ID Type / Status
Subject John I, Count of Holland E290964 entity
Predicate givenName P17 FINISHED
Object John
John I, Count of Holland, was a medieval nobleman who ruled the County of Holland at the turn of the 14th century.
E972143 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, Count of Holland, givenName, John]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John
Context triple: [John I, Count of Holland, givenName, John]
  • A. John
    John is the given name of John J. Pershing, the famed American general who led the American Expeditionary Forces in World War I.
  • B. John
    John is the given name of John A. Roebling II, an American civil engineer and philanthropist from the prominent Roebling family associated with major bridge construction.
  • C. John
    John is the given first name of Johnny Kilbane, an American featherweight boxing champion from the early 20th century.
  • D. John
    John is the given name of John Albert William Spencer-Churchill, a British aristocrat and 10th Duke of Marlborough.
  • E. John
    John is the given name of John Williams Walker, an early 19th-century American politician and U.S. Senator from Alabama.
  • 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, Count of Holland, givenName, John]
Generated description
John I, Count of Holland, was a medieval nobleman who ruled the County of Holland at the turn of the 14th century.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: John
Target entity description: John I, Count of Holland, was a medieval nobleman who ruled the County of Holland at the turn of the 14th century.
  • A. 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.
  • B. John
    John V, Duke of Brittany, was a 15th-century French nobleman who ruled the Duchy of Brittany and played a significant role in the politics of the Hundred Years' War.
  • C. John
    John of Montfort was a 14th-century nobleman involved in the Breton succession disputes during the Hundred Years’ War.
  • D. John
    John III, Duke of Brittany, was a 14th-century French nobleman who ruled the Duchy of Brittany and played a key role in the succession disputes that led to the Breton War of Succession.
  • 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_69d6ab65923081909acfc61b7a612233 completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d91c915f548190b34a743f0a3bb51a completed April 10, 2026, 3:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69f60a62f0fc8190a3d15ccfb23bb788 completed May 2, 2026, 2:29 p.m.
NEDg Description generation batch_69f6128da2c4819095bef0cb02a3d39d completed May 2, 2026, 3:04 p.m.
NED2 Entity disambiguation (via description) batch_69f6134f17c88190a17e1672b9eb2191 completed May 2, 2026, 3:07 p.m.
Created at: April 8, 2026, 9:51 p.m.