Triple

T4556521
Position Surface form Disambiguated ID Type / Status
Subject Lord Protector E120492 entity
Predicate capital P234 FINISHED
Object London E1817 NE FINISHED

How this triple was built (2 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: [Lord Protector, capital, London]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: London
Context triple: [Lord Protector, 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 chosen
    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.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69bd4636f1648190a701445c2fcd9c17 completed March 20, 2026, 1:05 p.m.
NER Named-entity recognition batch_69bd5814f56c8190a65f61f6148b7e5a completed March 20, 2026, 2:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdc564452c819080beada43c9ba7b1 completed March 20, 2026, 10:08 p.m.
Created at: March 20, 2026, 1:09 p.m.