Triple

T8416296
Position Surface form Disambiguated ID Type / Status
Subject Oceania E198737 entity
Predicate capital P234 FINISHED
Object London
London is a major city in Kiribati, located on Kiritimati (Christmas Island) in the central Pacific Ocean.
E737731 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: London | Statement: [Oceania, capital, London]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: London
Context triple: [Oceania, capital, London]
  • A. London
    London is a major Ethereum network upgrade that introduced significant changes to the protocol’s fee market and transaction pricing mechanisms.
  • B. London, England
    London, England is the capital and largest city of the United Kingdom, renowned as a global center for finance, culture, and politics.
  • C. Allondon
    Allondon is a small river in western Switzerland and neighboring France, known for flowing through the Geneva region and its natural, relatively unspoiled surroundings.
  • D. York, England
    York, England is a historic walled city in northern England renowned for its medieval architecture, including York Minster, and its rich Roman and Viking heritage.
  • E. Λούγδουνον
    Λούγδουνον is the ancient Greek name for Lugdunum, the major Roman city that developed into modern-day Lyon in France.
  • 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: London
Triple: [Oceania, capital, London]
Generated description
London is a major city in Kiribati, located on Kiritimati (Christmas Island) in the central Pacific Ocean.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: London
Target entity description: London is a major city in Kiribati, located on Kiritimati (Christmas Island) in the central Pacific Ocean.
  • A. London
    London is a major Ethereum network upgrade that introduced significant changes to the protocol’s fee market and transaction pricing mechanisms.
  • B. London, England
    London, England is the capital and largest city of the United Kingdom, renowned as a global center for finance, culture, and politics.
  • C. Allondon
    Allondon is a small river in western Switzerland and neighboring France, known for flowing through the Geneva region and its natural, relatively unspoiled surroundings.
  • D. York, England
    York, England is a historic walled city in northern England renowned for its medieval architecture, including York Minster, and its rich Roman and Viking heritage.
  • E. Λούγδουνον
    Λούγδουνον is the ancient Greek name for Lugdunum, the major Roman city that developed into modern-day Lyon in France.
  • 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_69ca831201b481909e137936ef99ff11 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cb84c5121081908efa3eca25406d3a completed March 31, 2026, 8:24 a.m.
NED1 Entity disambiguation (via context triple) batch_69ce4d731b248190a440e1289e655b74 completed April 2, 2026, 11:05 a.m.
NEDg Description generation batch_69ce4f587a7081908c357f82bc28a1aa completed April 2, 2026, 11:13 a.m.
NED2 Entity disambiguation (via description) batch_69ce5059e0f48190b8ff08253337f430 completed April 2, 2026, 11:17 a.m.
Created at: March 30, 2026, 6:06 p.m.