Triple

T14277329
Position Surface form Disambiguated ID Type / Status
Subject Sherborne E353947 entity
Predicate hasRiver P165 FINISHED
Object River Yeo
River Yeo is a small river in southwest England that flows through parts of Dorset and Somerset, including the town of Sherborne.
E1096494 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 Yeo | Statement: [Sherborne, hasRiver, River Yeo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: River Yeo
Context triple: [Sherborne, hasRiver, River Yeo]
  • A. River Yeo
    River Yeo is a small river in North Somerset, England, that flows through rural villages and farmland before joining the River Avon system.
  • B. Yeong River
    The Yeong River is a river in South Korea that feeds into the larger Nakdong River system.
  • C. Yong River
    The Yong River is a major waterway in Guangxi, China, flowing through the regional capital Nanning and playing an important role in its transport, ecology, and urban landscape.
  • D. Geum River
    The Geum River is a major river in western South Korea that flows through the central region before emptying into the Yellow Sea.
  • E. Louhajang River
    The Louhajang River is a regional waterway in central Bangladesh that flows through Tangail District and supports local agriculture, fisheries, and transportation.
  • 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 Yeo
Triple: [Sherborne, hasRiver, River Yeo]
Generated description
River Yeo is a small river in southwest England that flows through parts of Dorset and Somerset, including the town of Sherborne.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: River Yeo
Target entity description: River Yeo is a small river in southwest England that flows through parts of Dorset and Somerset, including the town of Sherborne.
  • A. River Yeo
    River Yeo is a small river in North Somerset, England, that flows through rural villages and farmland before joining the River Avon system.
  • B. Yeong River
    The Yeong River is a river in South Korea that feeds into the larger Nakdong River system.
  • C. Yong River
    The Yong River is a major waterway in Guangxi, China, flowing through the regional capital Nanning and playing an important role in its transport, ecology, and urban landscape.
  • D. Geum River
    The Geum River is a major river in western South Korea that flows through the central region before emptying into the Yellow Sea.
  • E. Louhajang River
    The Louhajang River is a regional waterway in central Bangladesh that flows through Tangail District and supports local agriculture, fisheries, and transportation.
  • 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_69d8278d25148190abf1a8c8f5f533ad completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de6583f0ec81909ebfc7a2c6351ff8 completed April 14, 2026, 4:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd550234408190ba10bd360bfa3f23 completed May 8, 2026, 3:14 a.m.
NEDg Description generation batch_69fd5599129081909924d1bf8491544c completed May 8, 2026, 3:16 a.m.
NED2 Entity disambiguation (via description) batch_69fd563bd8b48190a6420071b908efbe completed May 8, 2026, 3:19 a.m.
Created at: April 10, 2026, 1:10 a.m.