Triple

T6106136
Position Surface form Disambiguated ID Type / Status
Subject South Region E136121 entity
Predicate hasCapital P204 FINISHED
Object Ebolowa
Ebolowa is a city in southern Cameroon that serves as an administrative and commercial center for the surrounding agricultural region.
 E568529 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: Ebolowa | Statement: [South Region, hasCapital, Ebolowa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Ebolowa
Context triple: [South Region, hasCapital, Ebolowa]
  • A. Benina
    Benina is a town in eastern Libya that serves as the main gateway to the nearby city of Benghazi through its international airport.
  • B. Abéché
    Abéché is a major city in eastern Chad that serves as an important regional trade and administrative center.
  • C. Ewondo
    Ewondo is a Bantu language spoken primarily by the Ewondo people in central Cameroon, including in and around the capital city, Yaoundé.
  • D. Calabar
    Calabar is a historic port city in southeastern Nigeria known for its role in the transatlantic slave trade and its vibrant cultural festivals.
  • E. Ebanga
    Ebanga is a monoclonal antibody drug used to treat Zaire ebolavirus infection (Ebola virus disease).
  • 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: Ebolowa
Triple: [South Region, hasCapital, Ebolowa]
Generated description
Ebolowa is a city in southern Cameroon that serves as an administrative and commercial center for the surrounding agricultural region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Ebolowa
Target entity description: Ebolowa is a city in southern Cameroon that serves as an administrative and commercial center for the surrounding agricultural region.
  • A. Benina
    Benina is a town in eastern Libya that serves as the main gateway to the nearby city of Benghazi through its international airport.
  • B. Abéché
    Abéché is a major city in eastern Chad that serves as an important regional trade and administrative center.
  • C. Ewondo
    Ewondo is a Bantu language spoken primarily by the Ewondo people in central Cameroon, including in and around the capital city, Yaoundé.
  • D. Calabar
    Calabar is a historic port city in southeastern Nigeria known for its role in the transatlantic slave trade and its vibrant cultural festivals.
  • E. Ebanga
    Ebanga is a monoclonal antibody drug used to treat Zaire ebolavirus infection (Ebola virus disease).
  • 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_69c0087dee9881909e3655be88208c01 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c05b7ee8b48190b87f5ec8a46d6e2d completed March 22, 2026, 9:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69c1255759f48190a6aadf33406dcb49 completed March 23, 2026, 11:34 a.m.
NEDg Description generation batch_69c1275910108190a0a5f458a468c292 completed March 23, 2026, 11:43 a.m.
NED2 Entity disambiguation (via description) batch_69c127b831d081909436a62e002d1fa5 completed March 23, 2026, 11:44 a.m.
Created at: March 22, 2026, 4:13 p.m.