Triple

T21588052
Position Surface form Disambiguated ID Type / Status
Subject Kisukuma language E532703 entity
Predicate hasDialect P4251 FINISHED
Object Kanda
Kanda is a dialect of the Kisukuma language spoken by the Sukuma people of Tanzania.
E1500678 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: Kanda | Statement: [Kisukuma language, hasDialect, Kanda]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kanda
Context triple: [Kisukuma language, hasDialect, Kanda]
  • A. Kanda
    Kanda is a historic commercial and educational district in central Tokyo known for its bookstores, universities, and traditional shrines.
  • B. Kanda
    Kanda is a town in Fukuoka Prefecture, Japan, that forms part of the broader Fukuoka-Kitakyushu urban and industrial region on Kyushu.
  • C. Urakawa
    Urakawa is a coastal town in Hokkaido, Japan, known for its horse breeding industry and scenic Pacific shoreline.
  • D. Daidō
    Daidō was a Japanese era name (nengō) from the early Heian period, used during the reign of Emperor Kanmu.
  • E. Daidō
    Daidō was a Japanese era name (nengō) of the early 9th century, used during the reign of Emperor Saga.
  • 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: Kanda
Triple: [Kisukuma language, hasDialect, Kanda]
Generated description
Kanda is a dialect of the Kisukuma language spoken by the Sukuma people of Tanzania.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kanda
Target entity description: Kanda is a dialect of the Kisukuma language spoken by the Sukuma people of Tanzania.
  • A. Kanda
    Kanda is a historic commercial and educational district in central Tokyo known for its bookstores, universities, and traditional shrines.
  • B. Kanda
    Kanda is a town in Fukuoka Prefecture, Japan, that forms part of the broader Fukuoka-Kitakyushu urban and industrial region on Kyushu.
  • C. Urakawa
    Urakawa is a coastal town in Hokkaido, Japan, known for its horse breeding industry and scenic Pacific shoreline.
  • D. Daidō
    Daidō was a Japanese era name (nengō) from the early Heian period, used during the reign of Emperor Kanmu.
  • E. Daidō
    Daidō was a Japanese era name (nengō) of the early 9th century, used during the reign of Emperor Saga.
  • 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_69e0c46251648190876f0427cf2d321b completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69eeeb621ab88190a33a943424ffb306 completed April 27, 2026, 4:51 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0a365fe33c819096614a37427a1fd7 completed May 17, 2026, 9:42 p.m.
NEDg Description generation batch_6a0a3728a37c8190b9c7a296816709bd completed May 17, 2026, 9:46 p.m.
NED2 Entity disambiguation (via description) batch_6a0a37f8c09c8190a92f78909cfbc6e7 completed May 17, 2026, 9:49 p.m.
Created at: April 16, 2026, 6:31 p.m.