Triple

T7879115
Position Surface form Disambiguated ID Type / Status
Subject Accra Sports Stadium E182932 entity
Predicate capitalOf P204 FINISHED
Object Ghana E23760 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: Ghana | Statement: [Accra Sports Stadium, capitalOf, Ghana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ghana
Context triple: [Accra Sports Stadium, capitalOf, Ghana]
  • A. Ghana chosen
    Ghana is a West African nation known for being the first sub-Saharan African country to gain independence from colonial rule and for its stable democracy and rich cultural heritage.
  • B. Anyako, Ghana
    Anyako, Ghana is a small coastal town in the Volta Region known as the hometown of internationally acclaimed sculptor El Anatsui.
  • C. Côte d'Ivoire
    Côte d'Ivoire is a West African country on the Gulf of Guinea known for its cocoa production, diverse cultures, and economic prominence in the region.
  • D. Guinea
    Guinea is a West African country on the Atlantic coast known for its rich mineral resources, diverse ethnic groups, and role as a major producer of bauxite.
  • E. Costa d’Oiro
    Costa d’Oiro is a scenic coastal area near Lagos in Portugal’s Algarve region, known for its golden cliffs, sheltered coves, and picturesque beaches.
  • 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_69ca828a17248190b46defe758bc5ad3 completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb39be7ab88190affcd353a0cd37fa completed March 31, 2026, 3:04 a.m.
NED1 Entity disambiguation (via context triple) batch_69cc561d31888190bae66fb009ace1a1 completed March 31, 2026, 11:17 p.m.
Created at: March 30, 2026, 4:57 p.m.