Triple

T15612303
Position Surface form Disambiguated ID Type / Status
Subject Manyara Region E375327 entity
Predicate capital P234 FINISHED
Object Babati
Babati is a town in northern Tanzania that serves as an administrative and commercial hub near Lake Babati and the Tarangire National Park.
 E1166041 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: Babati | Statement: [Manyara Region, capital, Babati]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Babati
Context triple: [Manyara Region, capital, Babati]
  • A. Omuta
    Omuta is an industrial city in southern Fukuoka Prefecture, Japan, historically known for its coal mining and chemical industries.
  • B. Likasi
    Likasi is a mining city in the southeastern Democratic Republic of the Congo, known for its significant copper and cobalt production.
  • C. Mandera
    Mandera is a remote town in northeastern Kenya near the borders with Somalia and Ethiopia, serving as a key regional trading and administrative center.
  • D. Nyamwezi
    Nyamwezi is a Bantu language spoken primarily in northwestern Tanzania by the Nyamwezi people.
  • E. Tabora
    Tabora is a historic town in western Tanzania known as a regional trade center and former hub of 19th-century caravan routes.
  • 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: Babati
Triple: [Manyara Region, capital, Babati]
Generated description
Babati is a town in northern Tanzania that serves as an administrative and commercial hub near Lake Babati and the Tarangire National Park.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Babati
Target entity description: Babati is a town in northern Tanzania that serves as an administrative and commercial hub near Lake Babati and the Tarangire National Park.
  • A. Omuta
    Omuta is an industrial city in southern Fukuoka Prefecture, Japan, historically known for its coal mining and chemical industries.
  • B. Likasi
    Likasi is a mining city in the southeastern Democratic Republic of the Congo, known for its significant copper and cobalt production.
  • C. Mandera
    Mandera is a remote town in northeastern Kenya near the borders with Somalia and Ethiopia, serving as a key regional trading and administrative center.
  • D. Nyamwezi
    Nyamwezi is a Bantu language spoken primarily in northwestern Tanzania by the Nyamwezi people.
  • E. Tabora
    Tabora is a historic town in western Tanzania known as a regional trade center and former hub of 19th-century caravan routes.
  • 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_69d85ccf2794819096cda4cbcb02d478 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04e8148a0819087d6d69cc84487ca completed April 16, 2026, 2:50 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff56d91f208190a11f0d208970145b completed May 9, 2026, 3:46 p.m.
NEDg Description generation batch_69ff57f1b5488190a3200ec3707b0eee completed May 9, 2026, 3:51 p.m.
NED2 Entity disambiguation (via description) batch_69ff585cff9081908e7ce481cc653167 completed May 9, 2026, 3:53 p.m.
Created at: April 10, 2026, 4:13 a.m.