Triple

T16794590
Position Surface form Disambiguated ID Type / Status
Subject Northern Region of Ghana E408199 entity
Predicate contains P35 FINISHED
Object Walewale
Walewale is a town in northern Ghana that serves as a key local commercial and administrative center.
 E1235140 NE FINISHED

How this triple was built (4 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: Walewale | Statement: [Northern Region of Ghana, contains, Walewale]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Walewale
Context triple: [Northern Region of Ghana, contains, Walewale]
  • A. Walili
    Walili, better known as Volubilis, is an ancient Roman and early Islamic city in present-day Morocco that served as the first capital of the Idrisid dynasty.
  • B. Manggalili
    Manggalili is a Yolŋu Aboriginal Australian language associated with the Manggalili clan of northeast Arnhem Land in the Northern Territory.
  • C. Bwiro
    Bwiro is a settlement located within Ukerewe District in Tanzania’s Mwanza Region.
  • D. Kwaluudhi
    Kwaluudhi is a dialect of the Ovambo language spoken by a specific Ovambo subgroup in northern Namibia.
  • E. Kinkala
    Kinkala is a town in the Republic of the Congo that serves as an administrative and economic center for the surrounding region.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Walewale
Triple: [Northern Region of Ghana, contains, Walewale]
Generated description
Walewale is a town in northern Ghana that serves as a key local commercial and administrative center.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Walewale
Target entity description: Walewale is a town in northern Ghana that serves as a key local commercial and administrative center.
  • A. Walili
    Walili, better known as Volubilis, is an ancient Roman and early Islamic city in present-day Morocco that served as the first capital of the Idrisid dynasty.
  • B. Manggalili
    Manggalili is a Yolŋu Aboriginal Australian language associated with the Manggalili clan of northeast Arnhem Land in the Northern Territory.
  • C. Bwiro
    Bwiro is a settlement located within Ukerewe District in Tanzania’s Mwanza Region.
  • D. Kwaluudhi
    Kwaluudhi is a dialect of the Ovambo language spoken by a specific Ovambo subgroup in northern Namibia.
  • E. Kinkala
    Kinkala is a town in the Republic of the Congo that serves as an administrative and economic center for the surrounding region.
  • F. None of above. chosen

Provenance (5 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_69d88393905081908d00a86b99996ac8 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3b2a8b66c8190b83d8af85d2b23a8 completed April 18, 2026, 4:34 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00b28b77188190b8d87fca1b5dde5d completed May 10, 2026, 4:30 p.m.
NEDg Description generation batch_6a00b32d2a588190b59bad56f8817bce completed May 10, 2026, 4:32 p.m.
NED2 Entity disambiguation (via description) batch_6a00b3d14b3c819081f435777f47eca3 completed May 10, 2026, 4:35 p.m.
Created at: April 10, 2026, 5:22 a.m.