Triple

T7911501
Position Surface form Disambiguated ID Type / Status
Subject Mbeya Region E183708 entity
Predicate hasCity P316 FINISHED
Object Kyela
Kyela is a town and district in southern Tanzania known for its fertile land, rice production, and location near the northern shores of Lake Nyasa.
 E696714 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: Kyela | Statement: [Mbeya Region, hasCity, Kyela]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kyela
Context triple: [Mbeya Region, hasCity, Kyela]
  • A. Kadina
    Kadina is a historic copper mining town and one of the main commercial centers on South Australia's Yorke Peninsula.
  • B. Caelum
    Caelum is a small, faint southern constellation introduced in the 18th century, representing a sculptor’s chisel.
  • C. Rovenna
    Rovenna is a small village and frazione of the municipality of Cernobbio in the Province of Como, Lombardy, northern Italy.
  • D. Mylasa
    Mylasa was an important ancient city of Caria in southwestern Anatolia, known as a political and religious center, particularly for the worship of Zeus.
  • E. Keila
    Keila is a small town in northern Estonia known for its historic church, scenic Keila River and waterfall, and role as a local administrative and transport hub.
  • 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: Kyela
Triple: [Mbeya Region, hasCity, Kyela]
Generated description
Kyela is a town and district in southern Tanzania known for its fertile land, rice production, and location near the northern shores of Lake Nyasa.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kyela
Target entity description: Kyela is a town and district in southern Tanzania known for its fertile land, rice production, and location near the northern shores of Lake Nyasa.
  • A. Kadina
    Kadina is a historic copper mining town and one of the main commercial centers on South Australia's Yorke Peninsula.
  • B. Caelum
    Caelum is a small, faint southern constellation introduced in the 18th century, representing a sculptor’s chisel.
  • C. Rovenna
    Rovenna is a small village and frazione of the municipality of Cernobbio in the Province of Como, Lombardy, northern Italy.
  • D. Mylasa
    Mylasa was an important ancient city of Caria in southwestern Anatolia, known as a political and religious center, particularly for the worship of Zeus.
  • E. Keila
    Keila is a small town in northern Estonia known for its historic church, scenic Keila River and waterfall, and role as a local administrative and transport hub.
  • 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_69ca828dec0c81908b8f55a4dbbb53ff completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb3a725b8c8190a530adb3107a95dd completed March 31, 2026, 3:07 a.m.
NED1 Entity disambiguation (via context triple) batch_69cb5bdaf91c8190b31c5e539bdf049f completed March 31, 2026, 5:30 a.m.
NEDg Description generation batch_69cb5f20eb3c81909e059d5a02263aa2 completed March 31, 2026, 5:44 a.m.
NED2 Entity disambiguation (via description) batch_69cb76aede388190a56e066c3302c35e completed March 31, 2026, 7:24 a.m.
Created at: March 30, 2026, 5:04 p.m.