Triple

T4527059
Position Surface form Disambiguated ID Type / Status
Subject Swerford E106204 entity
Predicate hasRiver P165 FINISHED
Object River Swere
River Swere is a small river in Oxfordshire, England, that flows through rural villages and countryside before joining the River Cherwell.
E449771 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: River Swere | Statement: [Swerford, hasRiver, River Swere]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: River Swere
Context triple: [Swerford, hasRiver, River Swere]
  • A. River Skane
    River Skane is a small Irish river known as a tributary of the historically significant River Boyne in eastern Ireland.
  • B. River Gade
    The River Gade is a chalk stream in Hertfordshire, England, flowing through towns such as Hemel Hempstead and Kings Langley before joining the River Colne.
  • C. Fyris River
    The Fyris River is a notable waterway in eastern Sweden that flows through the city of Uppsala and is closely associated with its history and landscape.
  • D. Arve River
    The Arve River is a glacial river in the Alps that flows through France and Switzerland, notably passing through Geneva before joining the Rhône.
  • E. Ångerman River
    The Ångerman River is a major river in northern Sweden known for its long course through forested landscapes before emptying into the Gulf of Bothnia.
  • 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: River Swere
Triple: [Swerford, hasRiver, River Swere]
Generated description
River Swere is a small river in Oxfordshire, England, that flows through rural villages and countryside before joining the River Cherwell.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: River Swere
Target entity description: River Swere is a small river in Oxfordshire, England, that flows through rural villages and countryside before joining the River Cherwell.
  • A. River Skane
    River Skane is a small Irish river known as a tributary of the historically significant River Boyne in eastern Ireland.
  • B. River Gade
    The River Gade is a chalk stream in Hertfordshire, England, flowing through towns such as Hemel Hempstead and Kings Langley before joining the River Colne.
  • C. Fyris River
    The Fyris River is a notable waterway in eastern Sweden that flows through the city of Uppsala and is closely associated with its history and landscape.
  • D. Arve River
    The Arve River is a glacial river in the Alps that flows through France and Switzerland, notably passing through Geneva before joining the Rhône.
  • E. Ångerman River
    The Ångerman River is a major river in northern Sweden known for its long course through forested landscapes before emptying into the Gulf of Bothnia.
  • 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_69bd43f3d6e08190a91824f833d51bbe completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd57760f4481908f69ce82be63d7f8 completed March 20, 2026, 2:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69bda4577d0c8190a88cdf4523446329 completed March 20, 2026, 7:47 p.m.
NEDg Description generation batch_69bda8367b988190bd6859581ba9a38e completed March 20, 2026, 8:04 p.m.
NED2 Entity disambiguation (via description) batch_69bda8b4d064819083de58ee18458fa8 completed March 20, 2026, 8:06 p.m.
Created at: March 20, 2026, 1:03 p.m.