Triple

T14127777
Position Surface form Disambiguated ID Type / Status
Subject Thomas of Lancaster, 1st Duke of Clarence E340077 entity
Predicate burialPlace P196 FINISHED
Object Kent
Kent is a historic county in southeastern England, often called the "Garden of England," known for its rich history, coastal towns, and agricultural landscapes.
 E5977 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: Kent | Statement: [Thomas of Lancaster, 1st Duke of Clarence, burialPlace, Kent]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kent
Context triple: [Thomas of Lancaster, 1st Duke of Clarence, burialPlace, Kent]
  • A. Kent
    Kent is a suburban city in King County, Washington, known as a residential and industrial hub within the greater Seattle metropolitan area.
  • B. Kent
    Kent is the middle name of American basketball executive and former Boston Celtics head coach Brad Stevens.
  • C. Kent
    Kent is a villainous saloon owner and primary antagonist in the classic 1939 Western film "Destry Rides Again."
  • D. Kent
    Kent is a small district municipality in British Columbia, Canada, known for its agricultural lands and proximity to the Fraser River.
  • E. Kent
    Kent is a brand of filtered cigarettes historically marketed as a "safer" smoking option and produced by the Lorillard Tobacco Company.
  • 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: Kent
Triple: [Thomas of Lancaster, 1st Duke of Clarence, burialPlace, Kent]
Generated description
Kent is a historic county in southeastern England, often called the "Garden of England," known for its rich history, coastal towns, and agricultural landscapes.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kent
Target entity description: Kent is a historic county in southeastern England, often called the "Garden of England," known for its rich history, coastal towns, and agricultural landscapes.
  • A. Kent chosen
    Kent is a county in southeastern England known for its historic towns, coastal landscapes, and nickname "the Garden of England."
  • B. Kent
    Kent is a small district municipality in British Columbia, Canada, known for its agricultural lands and proximity to the Fraser River.
  • C. Kent
    Kent is a suburban city in King County, Washington, known as a residential and industrial hub within the greater Seattle metropolitan area.
  • D. Kent
    Kent is a common English surname borne by numerous notable individuals across fields such as art, politics, and entertainment.
  • E. Kent
    Kent is a common English surname famously associated with the adoptive family of Superman in DC Comics, including Jonathan and Martha Kent.
  • 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_69d81c6a95b481909e39111e0c1f31ee completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de6098013c8190b1bac9d3fff60acd completed April 14, 2026, 3:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcdefe88b481908b3dca1f019e7809 completed May 7, 2026, 6:50 p.m.
NEDg Description generation batch_69fce15e4d4c8190916ab384f37e7b11 completed May 7, 2026, 7 p.m.
NED2 Entity disambiguation (via description) batch_69fce1d5906c8190bd39e08861b9f53e completed May 7, 2026, 7:02 p.m.
Created at: April 9, 2026, 10:22 p.m.