Triple

T6130474
Position Surface form Disambiguated ID Type / Status
Subject A57 road E136703 entity
Predicate connectsCity P4245 FINISHED
Object Lincoln
Lincoln is a historic cathedral city in Lincolnshire, England, known for its medieval architecture, including Lincoln Cathedral and Lincoln Castle.
 E116393 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: Lincoln | Statement: [A57 road, connectsCity, Lincoln]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Lincoln
Context triple: [A57 road, connectsCity, Lincoln]
  • A. Lincoln
    Lincoln is a suburban town in eastern Massachusetts known for its conservation land, historic sites, and commuter access to Boston.
  • B. Lincoln
    Lincoln is a luxury automobile marque of the Ford Motor Company known for its premium sedans and SUVs.
  • C. Lincoln
    Lincoln is a common English surname most famously associated with U.S. President Abraham Lincoln and his family.
  • D. Lincoln
    Lincoln is a suburban town in Providence County, Rhode Island, known for its historic mill villages, residential neighborhoods, and recreational areas such as Lincoln Woods State Park.
  • E. Lincoln
    Lincoln is a masculine given name of English origin most famously associated with U.S. President Abraham Lincoln.
  • 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: Lincoln
Triple: [A57 road, connectsCity, Lincoln]
Generated description
Lincoln is a historic cathedral city in Lincolnshire, England, known for its medieval architecture, including Lincoln Cathedral and Lincoln Castle.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Lincoln
Target entity description: Lincoln is a historic cathedral city in Lincolnshire, England, known for its medieval architecture, including Lincoln Cathedral and Lincoln Castle.
  • A. Lincoln chosen
    Lincoln is a historic cathedral city in the East Midlands of England, renowned for its medieval architecture, including Lincoln Cathedral and Lincoln Castle.
  • B. Lincoln
    Lincoln is a historic American city in Illinois best known as the namesake of President Abraham Lincoln and for its rich Civil War–era heritage.
  • C. Lincoln
    Lincoln is a suburban town in eastern Massachusetts known for its conservation land, historic sites, and commuter access to Boston.
  • D. Lincoln
    Lincoln is a suburban town in Providence County, Rhode Island, known for its historic mill villages, residential neighborhoods, and recreational areas such as Lincoln Woods State Park.
  • E. Lincoln
    Lincoln is a common English surname most famously associated with U.S. President Abraham Lincoln and his 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_69c008a0a37c81908e5b4f879158afb3 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c05c4de9c48190b98f67a6251ec1df completed March 22, 2026, 9:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69c1416a4dd481908f1336fbd02c7af8 completed March 23, 2026, 1:34 p.m.
NEDg Description generation batch_69c1470b2cc08190b933acd0855ca0ef completed March 23, 2026, 1:58 p.m.
NED2 Entity disambiguation (via description) batch_69c1477308988190a49f830a4473c775 completed March 23, 2026, 2 p.m.
Created at: March 22, 2026, 4:15 p.m.