Triple

T5907054
Position Surface form Disambiguated ID Type / Status
Subject Leicester railway station E131365 entity
Predicate hasServiceTo P6787 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: [Leicester railway station, hasServiceTo, Lincoln]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Lincoln
Context triple: [Leicester railway station, hasServiceTo, 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: [Leicester railway station, hasServiceTo, 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_69c0085864a88190a569c05ff7d65f29 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c03772d9dc8190899fe49ef887e685 completed March 22, 2026, 6:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69c1134e27388190ad90faed28d2d360 completed March 23, 2026, 10:17 a.m.
NEDg Description generation batch_69c1176428608190bf996b629e24a0cb completed March 23, 2026, 10:35 a.m.
NED2 Entity disambiguation (via description) batch_69c117f9d3848190a99cf0efc5d09114 completed March 23, 2026, 10:37 a.m.
Created at: March 22, 2026, 3:59 p.m.