Triple

T19802831
Position Surface form Disambiguated ID Type / Status
Subject River Douglas E475727 entity
Predicate isWaterBodyOf P1778 FINISHED
Object Douglas
Douglas is a town in Lancashire, England, historically associated with the nearby River Douglas and regional industrial development.
E1399693 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: Douglas | Statement: [River Douglas, isWaterBodyOf, Douglas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Douglas
Context triple: [River Douglas, isWaterBodyOf, Douglas]
  • A. Douglas
    Douglas is a town in South Lanarkshire, Scotland, historically known for its association with the powerful Douglas family and its medieval castle.
  • B. Douglas
    Douglas is a suburban area of Cork, Ireland, known as a residential and commercial hub just southeast of Cork city centre.
  • C. Douglas
    Douglas is a small rural community located within the township of Bonnechere Valley in eastern Ontario, Canada.
  • D. Douglas
    Douglas is a neighboring locality that forms part of the boundary of New City.
  • E. Douglas
    Douglas is a town that serves as the administrative center for the surrounding area, housing the Douglas Courthouse.
  • 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: Douglas
Triple: [River Douglas, isWaterBodyOf, Douglas]
Generated description
Douglas is a town in Lancashire, England, historically associated with the nearby River Douglas and regional industrial development.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Douglas
Target entity description: Douglas is a town in Lancashire, England, historically associated with the nearby River Douglas and regional industrial development.
  • A. Douglas
    Douglas is a town in South Lanarkshire, Scotland, historically known for its association with the powerful Douglas family and its medieval castle.
  • B. Douglas
    Douglas is a small town in South Africa’s Northern Cape province, situated near the confluence of the Orange and Vaal Rivers and known for its agricultural activities.
  • C. Douglas
    Douglas is a town that serves as the administrative center for the surrounding area, housing the Douglas Courthouse.
  • D. Douglas
    Douglas is a community area on the South Side of Chicago, Illinois, known for its historic residential neighborhoods and proximity to the city’s lakefront.
  • E. Douglas
    Douglas is a small rural community located within the township of Bonnechere Valley in eastern Ontario, Canada.
  • 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_69d8e51bc4208190a1c57d8c5d1b15e4 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e654257cb4819096fb2aa5d1f7fbb0 completed April 20, 2026, 4:28 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07dbb522488190bda92082bed544ec completed May 16, 2026, 2:51 a.m.
NEDg Description generation batch_6a07dc854a0c8190b0da81ead6b9cfc1 completed May 16, 2026, 2:55 a.m.
NED2 Entity disambiguation (via description) batch_6a07dd45e93c8190b14c23487398a8ec completed May 16, 2026, 2:58 a.m.
Created at: April 10, 2026, 1:49 p.m.