Triple

T14497199
Position Surface form Disambiguated ID Type / Status
Subject Blantyre E359531 entity
Predicate hasSuburb P747 FINISHED
Object Ndirande
Ndirande is a densely populated, historically significant township in Blantyre, Malawi, known for its vibrant informal economy and strong community identity.
 E1103252 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: Ndirande | Statement: [Blantyre, hasSuburb, Ndirande]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Ndirande
Context triple: [Blantyre, hasSuburb, Ndirande]
  • A. Ndiass
    Ndiass is a village in western Senegal that serves as the host community for Blaise Diagne International Airport, one of the country’s main air transport hubs.
  • B. Ndesandjo
    Ndesandjo is the surname of Mark Obama Ndesandjo, an American businessman, musician, and author who is the half-brother of former U.S. President Barack Obama.
  • C. Korandjé
    Korandjé is a highly endangered Northern Songhay language spoken in the oasis town of Tabelbala in southwestern Algeria.
  • D. Ngola
    Ngola is an alternative name for the Angolar people, a community of African descent primarily associated with São Tomé and Príncipe.
  • E. Ngoumbi
    Ngoumbi is an alternative name for the Kombe people, an ethnic group of Central Africa.
  • 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: Ndirande
Triple: [Blantyre, hasSuburb, Ndirande]
Generated description
Ndirande is a densely populated, historically significant township in Blantyre, Malawi, known for its vibrant informal economy and strong community identity.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Ndirande
Target entity description: Ndirande is a densely populated, historically significant township in Blantyre, Malawi, known for its vibrant informal economy and strong community identity.
  • A. Ndiass
    Ndiass is a village in western Senegal that serves as the host community for Blaise Diagne International Airport, one of the country’s main air transport hubs.
  • B. Ndesandjo
    Ndesandjo is the surname of Mark Obama Ndesandjo, an American businessman, musician, and author who is the half-brother of former U.S. President Barack Obama.
  • C. Korandjé
    Korandjé is a highly endangered Northern Songhay language spoken in the oasis town of Tabelbala in southwestern Algeria.
  • D. Ngola
    Ngola is an alternative name for the Angolar people, a community of African descent primarily associated with São Tomé and Príncipe.
  • E. Ngoumbi
    Ngoumbi is an alternative name for the Kombe people, an ethnic group of Central Africa.
  • 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_69d8279740308190af9df93a3af8592e completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de9311cc748190880c784f173b7f2b completed April 14, 2026, 7:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd6d9731588190b27a826582e5fc6d completed May 8, 2026, 4:59 a.m.
NEDg Description generation batch_69fd6f82453481909a3e1b032f30a7a5 completed May 8, 2026, 5:07 a.m.
NED2 Entity disambiguation (via description) batch_69fd708521c881909863b7cd3fc4a313 completed May 8, 2026, 5:11 a.m.
Created at: April 10, 2026, 1:21 a.m.