Triple

T8591151
Position Surface form Disambiguated ID Type / Status
Subject EUCAP Somalia E203429 entity
Predicate hasFieldOffice P68855 FINISHED
Object Hargeisa E462624 NE FINISHED

How this triple was built (3 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: Hargeisa | Statement: [EUCAP Somalia, hasFieldOffice, Hargeisa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hargeisa
Context triple: [EUCAP Somalia, hasFieldOffice, Hargeisa]
  • A. Hargeisa chosen
    Hargeisa is the largest city and political, economic, and cultural center of the self-declared republic of Somaliland in the Horn of Africa.
  • B. Mogadishu
    Mogadishu is the capital and largest city of Somalia, serving as a major political, economic, and cultural center on the Horn of Africa.
  • C. Obock
    Obock is a coastal town in northeastern Djibouti, situated on the Gulf of Tadjoura and known historically as one of the country’s earliest French colonial settlements.
  • D. Burao
    Burao is a key commercial and administrative city in central Somaliland, known as a major livestock trading hub in the region.
  • E. Nouakchott
    Nouakchott is the capital and largest city of Mauritania, located on the Atlantic coast of Northwest Africa.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasFieldOffice
Context triple: [EUCAP Somalia, hasFieldOffice, Hargeisa]
  • A. hasAssociatedOffice
    Indicates that an entity is linked to or connected with a particular office in an official or functional capacity.
  • B. hasSupportingOffice
    Indicates that an entity is associated with or served by a particular office that provides support or administrative services to it.
  • C. hasBranchOffice chosen
    Indicates that one organization maintains a branch office or subsidiary location in another place or entity.
  • D. hasProperOffice
    Indicates that an entity maintains an officially designated, appropriate office or place of business.
  • E. hasCorporateOffice
    Indicates that an entity maintains a formal corporate office at a specified location or within another organizational entity.
  • F. None of above.

Provenance (4 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_69ca832a7f108190b4e4f5648abf4aa2 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cc46c5e8888190b721e791c449b0df completed March 31, 2026, 10:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69cebb9ef3ac819098810294e6bc34a7 completed April 2, 2026, 6:55 p.m.
PD Predicate disambiguation batch_69cc454504448190aaad2af8b17357cd completed March 31, 2026, 10:05 p.m.
Created at: March 30, 2026, 6:23 p.m.