Triple

T23521278
Position Surface form Disambiguated ID Type / Status
Subject Tamale E574512 entity
Predicate connectsByRoadTo P11435 FINISHED
Object Bolgatanga NE NERFINISHED

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: Bolgatanga | Statement: [Tamale, connectsByRoadTo, Bolgatanga]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bolgatanga
Context triple: [Tamale, connectsByRoadTo, Bolgatanga]
  • A. Bolgatanga chosen
    Bolgatanga is a town in northern Ghana known as a commercial and cultural hub, particularly famous for its traditional crafts and vibrant market.
  • B. Kaolack
    Kaolack is a major city in western Senegal known as a regional commercial hub and center of peanut trade.
  • C. Atebubu
    Atebubu is a prominent market and administrative town in central Ghana, serving as a key commercial hub in the Bono East area.
  • D. Dangme
    Dangme is a Kwa language spoken primarily by the Dangme people in southeastern Ghana.
  • E. Kenema
    Kenema is a major city in eastern Sierra Leone, serving as the capital and economic center of Kenema District and a hub for trade and agriculture.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e245bb3dcc8190ba9a2b35972b58d0 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1aa873ad48190a86807bd4f26df82 completed April 29, 2026, 6:51 a.m.
Created at: April 17, 2026, 6:08 p.m.