Triple

T20057837
Position Surface form Disambiguated ID Type / Status
Subject Brent Reservoir E499386 entity
Predicate inflow P415 FINISHED
Object Silk Stream
Silk Stream is a small river in northwest London that serves as a tributary to the Brent Reservoir and ultimately the River Brent.
 E1408578 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: Silk Stream | Statement: [Brent Reservoir, inflow, Silk Stream]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Silk Stream
Context triple: [Brent Reservoir, inflow, Silk Stream]
  • A. River Shiven
    River Shiven is a small river in western Ireland that flows through County Galway before joining the River Suck.
  • B. River Mur
    The River Mur is a major Central European river that flows through Austria, Slovenia, and Croatia before joining the Drava.
  • C. River Ill
    The River Ill is a major waterway in northeastern France that flows through the city of Strasbourg before joining the Rhine.
  • D. River Sow
    The River Sow is a river in Staffordshire, England, that flows through the town of Stafford before joining the River Trent.
  • E. Mill Stream
    Mill Stream is a scenic waterway running through Willamette University’s campus that serves as a central natural and aesthetic landmark for the university community.
  • 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: Silk Stream
Triple: [Brent Reservoir, inflow, Silk Stream]
Generated description
Silk Stream is a small river in northwest London that serves as a tributary to the Brent Reservoir and ultimately the River Brent.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Silk Stream
Target entity description: Silk Stream is a small river in northwest London that serves as a tributary to the Brent Reservoir and ultimately the River Brent.
  • A. River Shiven
    River Shiven is a small river in western Ireland that flows through County Galway before joining the River Suck.
  • B. River Mur
    The River Mur is a major Central European river that flows through Austria, Slovenia, and Croatia before joining the Drava.
  • C. River Ill
    The River Ill is a major waterway in northeastern France that flows through the city of Strasbourg before joining the Rhine.
  • D. River Sow
    The River Sow is a river in Staffordshire, England, that flows through the town of Stafford before joining the River Trent.
  • E. Mill Stream
    Mill Stream is a scenic waterway running through Willamette University’s campus that serves as a central natural and aesthetic landmark for the university community.
  • 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_69da6276bcf48190aabbf279192a5fb4 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e6637325908190aefc0e27e2ed5750 completed April 20, 2026, 5:33 p.m.
NED1 Entity disambiguation (via context triple) batch_6a08160e5fe481909cac91327be89022 completed May 16, 2026, 7 a.m.
NEDg Description generation batch_6a0816d3c71081909138d3144a108266 completed May 16, 2026, 7:03 a.m.
NED2 Entity disambiguation (via description) batch_6a08179df70c81908ea5bc596a8ba756 completed May 16, 2026, 7:07 a.m.
Created at: April 11, 2026, 3:38 p.m.