Triple

T1530096
Position Surface form Disambiguated ID Type / Status
Subject South African pound E32419 entity
Predicate partOf P40 FINISHED
Object sterling area E122377 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: sterling area | Statement: [South African pound, partOf, sterling area]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: sterling area
Context triple: [South African pound, partOf, sterling area]
  • A. Sterling area chosen
    The Sterling area was a post–World War II monetary bloc of countries and territories that pegged their currencies to the British pound and held their reserves largely in sterling.
  • B. London District
    London District is a British Army command responsible for overseeing military units and ceremonial duties in the Greater London area.
  • C. City of London
    The City of London is the historic and financial core of Greater London, renowned as one of the world’s leading global finance and business centers.
  • D. Middlesex, England
    Middlesex, England is a historic county in southeast England that once encompassed much of what is now Greater London.
  • E. Lothian
    Lothian is a historic region in southeastern Scotland that encompasses the capital city of Edinburgh and its surrounding areas.
  • 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_69a885ea86308190998f6bc14bb91f8e completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a908156b888190968ca0157ae42bc7 completed March 5, 2026, 4:35 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad2957e6e4819087504a16bc32d60b completed March 8, 2026, 7:46 a.m.
Created at: March 4, 2026, 7:26 p.m.