Triple

T2435465
Position Surface form Disambiguated ID Type / Status
Subject Germiston E52949 entity
Predicate locatedNear P294 FINISHED
Object Alberton
Alberton is a town in the East Rand region of Gauteng, South Africa, forming part of the greater Johannesburg metropolitan area.
E267317 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: Alberton | Statement: [Germiston, locatedNear, Alberton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Alberton
Context triple: [Germiston, locatedNear, Alberton]
  • A. Alloa
    Alloa is a town in central Scotland that serves as the main commercial and population hub of Clackmannanshire.
  • B. Dumbarton
    Dumbarton is a historic Scottish town on the River Clyde known for its prominent role in shipbuilding and maritime industry.
  • C. Clydebank
    Clydebank is a Scottish town on the River Clyde that was heavily industrialized and became notorious for the devastating air raids it suffered during the Second World War.
  • D. Larbert
    Larbert is a small town in central Scotland, situated in the Falkirk council area and historically known for its industrial heritage and transport links.
  • E. Innerleithen
    Innerleithen is a small Scottish Borders town known for its scenic setting in the Tweed Valley and its historic textile and milling heritage.
  • 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: Alberton
Triple: [Germiston, locatedNear, Alberton]
Generated description
Alberton is a town in the East Rand region of Gauteng, South Africa, forming part of the greater Johannesburg metropolitan area.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Alberton
Target entity description: Alberton is a town in the East Rand region of Gauteng, South Africa, forming part of the greater Johannesburg metropolitan area.
  • A. Alloa
    Alloa is a town in central Scotland that serves as the main commercial and population hub of Clackmannanshire.
  • B. Dumbarton
    Dumbarton is a historic Scottish town on the River Clyde known for its prominent role in shipbuilding and maritime industry.
  • C. Clydebank
    Clydebank is a Scottish town on the River Clyde that was heavily industrialized and became notorious for the devastating air raids it suffered during the Second World War.
  • D. Larbert
    Larbert is a small town in central Scotland, situated in the Falkirk council area and historically known for its industrial heritage and transport links.
  • E. Innerleithen
    Innerleithen is a small Scottish Borders town known for its scenic setting in the Tweed Valley and its historic textile and milling heritage.
  • 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_69ab4959bcc0819083246f9fb10439e3 completed March 6, 2026, 9:38 p.m.
NER Named-entity recognition batch_69abc9cd49b48190bff10a5ab7cef483 completed March 7, 2026, 6:46 a.m.
NED1 Entity disambiguation (via context triple) batch_69aef0a9790c81908b50fcae80def595 completed March 9, 2026, 4:09 p.m.
NEDg Description generation batch_69aef5b5f5dc8190bb721d8df5283faa completed March 9, 2026, 4:30 p.m.
NED2 Entity disambiguation (via description) batch_69aef6450a1c8190ad5a844b31bff220 completed March 9, 2026, 4:33 p.m.
Created at: March 6, 2026, 9:43 p.m.