Triple

T6177936
Position Surface form Disambiguated ID Type / Status
Subject Northern Region E137865 entity
Predicate capital P234 FINISHED
Object Tamale
Tamale is the largest city in northern Ghana and a major administrative, commercial, and cultural hub for the surrounding region.
 E574512 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: Tamale | Statement: [Northern Region, capital, Tamale]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tamale
Context triple: [Northern Region, capital, Tamale]
  • A. Menudo
    Menudo was a hugely popular Puerto Rican boy band formed in the late 1970s, known for its rotating lineup of young male singers and for launching the careers of several Latin pop stars.
  • B. Pastida
    Pastida is a small village on the Greek island of Rhodes, situated inland near the town of Ialysos and known for its traditional character and proximity to the island’s main tourist areas.
  • C. TACO
    TACO is a peer-reviewed scientific journal published by the ACM that focuses on research in computer architecture and code optimization.
  • D. Tejipió
    Tejipió is a neighborhood in the city of Recife, Brazil, known as part of the urban fabric of the state capital of Pernambuco.
  • E. Mexican Cocopa
    Mexican Cocopa is a regional variety of the Cocopa language spoken by Cocopa communities in northern Mexico.
  • 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: Tamale
Triple: [Northern Region, capital, Tamale]
Generated description
Tamale is the largest city in northern Ghana and a major administrative, commercial, and cultural hub for the surrounding region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tamale
Target entity description: Tamale is the largest city in northern Ghana and a major administrative, commercial, and cultural hub for the surrounding region.
  • A. Menudo
    Menudo was a hugely popular Puerto Rican boy band formed in the late 1970s, known for its rotating lineup of young male singers and for launching the careers of several Latin pop stars.
  • B. Pastida
    Pastida is a small village on the Greek island of Rhodes, situated inland near the town of Ialysos and known for its traditional character and proximity to the island’s main tourist areas.
  • C. TACO
    TACO is a peer-reviewed scientific journal published by the ACM that focuses on research in computer architecture and code optimization.
  • D. Tejipió
    Tejipió is a neighborhood in the city of Recife, Brazil, known as part of the urban fabric of the state capital of Pernambuco.
  • E. Mexican Cocopa
    Mexican Cocopa is a regional variety of the Cocopa language spoken by Cocopa communities in northern Mexico.
  • 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_69c008a80f748190ba3d07ffc81acb29 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c05dc9f3d88190ab46b3b246f5a8df completed March 22, 2026, 9:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69c141bb426881908d5a1451b3619f03 completed March 23, 2026, 1:35 p.m.
NEDg Description generation batch_69c1467ef4d48190b714823935318c0a completed March 23, 2026, 1:56 p.m.
NED2 Entity disambiguation (via description) batch_69c146f59d9881908fdc6c0137f0ead7 completed March 23, 2026, 1:58 p.m.
Created at: March 22, 2026, 4:18 p.m.