Triple

T11580481
Position Surface form Disambiguated ID Type / Status
Subject Borgu region E274612 entity
Predicate hasPart P35 FINISHED
Object Kandi
Kandi is a town and commune in northeastern Benin that serves as an important administrative and commercial center in the Borgu region.
 E934676 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: Kandi | Statement: [Borgu region, hasPart, Kandi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kandi
Context triple: [Borgu region, hasPart, Kandi]
  • A. Kandi
    Kandi is an American singer, songwriter, television personality, and businesswoman best known as a member of the R&B group Xscape and a star of The Real Housewives of Atlanta.
  • B. Niva
    Niva was a prominent Russian literary and illustrated weekly magazine of the late 19th and early 20th centuries, known for publishing fiction, poetry, and cultural commentary.
  • C. Azuga
    Azuga is a small mountain resort town in Romania known for its ski slopes and scenic location in the Carpathian Mountains.
  • D. Landy
    Landy is the official mascot character of the South Korean professional baseball team SSG Landers.
  • E. Citura
    Citura is the public transport operator responsible for managing Reims’ urban transit network, including its tramway system, in northeastern France.
  • 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: Kandi
Triple: [Borgu region, hasPart, Kandi]
Generated description
Kandi is a town and commune in northeastern Benin that serves as an important administrative and commercial center in the Borgu region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kandi
Target entity description: Kandi is a town and commune in northeastern Benin that serves as an important administrative and commercial center in the Borgu region.
  • A. Kandi
    Kandi is an American singer, songwriter, television personality, and businesswoman best known as a member of the R&B group Xscape and a star of The Real Housewives of Atlanta.
  • B. Niva
    Niva was a prominent Russian literary and illustrated weekly magazine of the late 19th and early 20th centuries, known for publishing fiction, poetry, and cultural commentary.
  • C. Azuga
    Azuga is a small mountain resort town in Romania known for its ski slopes and scenic location in the Carpathian Mountains.
  • D. Landy
    Landy is the official mascot character of the South Korean professional baseball team SSG Landers.
  • E. Citura
    Citura is the public transport operator responsible for managing Reims’ urban transit network, including its tramway system, in northeastern France.
  • 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_69d6aae5ac3c81908d2b0a3a665665b2 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8904c51b881909e7be84c6f3de79f completed April 10, 2026, 5:53 a.m.
NED1 Entity disambiguation (via context triple) batch_69e7141b16d8819099002a009260a85a completed April 21, 2026, 6:07 a.m.
NEDg Description generation batch_69e720f9a8588190aa766d2e1628207a completed April 21, 2026, 7:02 a.m.
NED2 Entity disambiguation (via description) batch_69e72315dda08190996aa84587c5fc80 completed April 21, 2026, 7:11 a.m.
Created at: April 8, 2026, 9:38 p.m.