Triple

T540184
Position Surface form Disambiguated ID Type / Status
Subject West Africa E12611 entity
Predicate hasMajorCity P316 FINISHED
Object Freetown
Freetown is the capital and largest city of Sierra Leone, known as a historic port and former center for resettled freed slaves in West Africa.
 E70581 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: Freetown | Statement: [West Africa, hasMajorCity, Freetown]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Freetown
Context triple: [West Africa, hasMajorCity, Freetown]
  • A. Monrovia
    Monrovia is the largest city and main economic and administrative center of Liberia, located on the Atlantic coast in West Africa.
  • B. Accra
    Accra is the capital and largest city of Ghana, known as a major economic, political, and cultural hub in West Africa.
  • C. Conakry
    Conakry is the capital and largest city of Guinea, serving as its main economic, cultural, and administrative center on the Atlantic coast of West Africa.
  • D. Bamako
    Bamako is the capital and largest city of Mali, serving as a major political, economic, and cultural center in West Africa.
  • E. Abidjan
    Abidjan is a major economic and cultural hub on the southern coast of Côte d'Ivoire, known for its bustling port, modern skyline, and status as one of the largest cities in West 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: Freetown
Triple: [West Africa, hasMajorCity, Freetown]
Generated description
Freetown is the capital and largest city of Sierra Leone, known as a historic port and former center for resettled freed slaves in West Africa.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Freetown
Target entity description: Freetown is the capital and largest city of Sierra Leone, known as a historic port and former center for resettled freed slaves in West Africa.
  • A. Monrovia
    Monrovia is the largest city and main economic and administrative center of Liberia, located on the Atlantic coast in West Africa.
  • B. Accra
    Accra is the capital and largest city of Ghana, known as a major economic, political, and cultural hub in West Africa.
  • C. Conakry
    Conakry is the capital and largest city of Guinea, serving as its main economic, cultural, and administrative center on the Atlantic coast of West Africa.
  • D. Bamako
    Bamako is the capital and largest city of Mali, serving as a major political, economic, and cultural center in West Africa.
  • E. Abidjan
    Abidjan is a major economic and cultural hub on the southern coast of Côte d'Ivoire, known for its bustling port, modern skyline, and status as one of the largest cities in West 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_69a49334226c81908b0ea1689ef6aa3f completed March 1, 2026, 7:27 p.m.
NER Named-entity recognition batch_69a4985feee481908184a39210feab95 completed March 1, 2026, 7:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69a4ed30d578819091c6c1f4c5eba301 completed March 2, 2026, 1:51 a.m.
NEDg Description generation batch_69a4edbab33881909369a7fc81165cf4 completed March 2, 2026, 1:54 a.m.
NED2 Entity disambiguation (via description) batch_69a4ee0f4e008190a9bdcc1ec93cefb3 completed March 2, 2026, 1:55 a.m.
Created at: March 1, 2026, 7:32 p.m.