Triple

T1474522
Position Surface form Disambiguated ID Type / Status
Subject African Development Bank E30807 entity
Predicate hasRegionalMemberCountries P17966 FINISHED
Object African Union member states LITERAL 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: African Union member states | Statement: [African Development Bank, hasRegionalMemberCountries, African Union member states]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasRegionalMemberCountries
Context triple: [African Development Bank, hasRegionalMemberCountries, African Union member states]
  • A. memberStatesAreMemberOf chosen
    Indicates that certain states belong to or hold membership in a particular organization, group, or union.
  • B. participantsRegion
    Indicates that the related entities are associated with, originate from, or operate within a specified geographic region.
  • C. countryJoined
    Indicates that a country became a member of, or formally entered into, a specific organization, union, alliance, or agreement.
  • D. countryOfOriginOfMembers
    Indicates that one entity is the country from which the members of another entity originate.
  • E. hasNumberOfCountries
    Indicates the relationship that specifies how many countries are associated with or contained within a given entity.
  • F. None of above.

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_69a498fe55a88190ab7f9e40ace88e49 completed March 1, 2026, 7:52 p.m.
NER Named-entity recognition batch_69a4c6011d248190988380eca4ecf514 completed March 1, 2026, 11:04 p.m.
PD Predicate disambiguation batch_69a4c48350d88190a81bd149103f93e3 completed March 1, 2026, 10:58 p.m.
Created at: March 1, 2026, 8:11 p.m.