Triple

T20054645
Position Surface form Disambiguated ID Type / Status
Subject Udzungwa Mountains National Park E499294 entity
Predicate accessPoint P1985 FINISHED
Object Mangula
Mangula is a settlement in southern Tanzania that serves as a primary gateway town for visitors entering Udzungwa Mountains National Park.
 E1410434 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: Mangula | Statement: [Udzungwa Mountains National Park, accessPoint, Mangula]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mangula
Context triple: [Udzungwa Mountains National Park, accessPoint, Mangula]
  • A. Mangole
    Mangole is one of the principal islands of Indonesia’s Sula Islands archipelago in North Maluku Province.
  • B. Mangamma
    Mangamma is an Indian surname commonly associated with South Indian families and traditional given names.
  • C. Muribenua
    Muribenua is a village on the low-lying coral atoll of Nikunau in the Republic of Kiribati, a Pacific island nation.
  • D. Moringua
    Moringua is a genus of slender, burrowing eels commonly known as spaghetti eels, found in tropical and subtropical marine waters.
  • E. Tamba
    Tamba is a city located in Hyogo Prefecture, Japan, known for its rural landscapes, traditional pottery, and historical sites.
  • 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: Mangula
Triple: [Udzungwa Mountains National Park, accessPoint, Mangula]
Generated description
Mangula is a settlement in southern Tanzania that serves as a primary gateway town for visitors entering Udzungwa Mountains National Park.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mangula
Target entity description: Mangula is a settlement in southern Tanzania that serves as a primary gateway town for visitors entering Udzungwa Mountains National Park.
  • A. Mangole
    Mangole is one of the principal islands of Indonesia’s Sula Islands archipelago in North Maluku Province.
  • B. Mangamma
    Mangamma is an Indian surname commonly associated with South Indian families and traditional given names.
  • C. Muribenua
    Muribenua is a village on the low-lying coral atoll of Nikunau in the Republic of Kiribati, a Pacific island nation.
  • D. Moringua
    Moringua is a genus of slender, burrowing eels commonly known as spaghetti eels, found in tropical and subtropical marine waters.
  • E. Tamba
    Tamba is a city located in Hyogo Prefecture, Japan, known for its rural landscapes, traditional pottery, and historical sites.
  • 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_69da6276bcf48190aabbf279192a5fb4 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66331c7488190840d43792ff09977 completed April 20, 2026, 5:32 p.m.
NED1 Entity disambiguation (via context triple) batch_6a081f31fcd88190a7ad0461610ebf57 completed May 16, 2026, 7:39 a.m.
NEDg Description generation batch_6a081fbb7f208190a032f9f312fd07de completed May 16, 2026, 7:41 a.m.
NED2 Entity disambiguation (via description) batch_6a08208c203c819083abea34d10d5e4e completed May 16, 2026, 7:45 a.m.
Created at: April 11, 2026, 3:38 p.m.