Triple

T5117742
Position Surface form Disambiguated ID Type / Status
Subject Kalunguta E115378 entity
Predicate publicHealthEmergency P18426 FINISHED
Object Kivu Ebola epidemic E19496 NE FINISHED

How this triple was built (3 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: Kivu Ebola epidemic | Statement: [Kalunguta, publicHealthEmergency, Kivu Ebola epidemic]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kivu Ebola epidemic
Context triple: [Kalunguta, publicHealthEmergency, Kivu Ebola epidemic]
  • A. 2018–2020 Kivu Ebola epidemic in the Democratic Republic of the Congo chosen
    The 2018–2020 Kivu Ebola epidemic in the Democratic Republic of the Congo was a major Ebola virus outbreak in the country’s conflict-affected eastern region that became the second-largest Ebola epidemic ever recorded and prompted a global emergency response.
  • B. 2007 Ebola outbreak in Democratic Republic of the Congo
    The 2007 Ebola outbreak in the Democratic Republic of the Congo was a deadly epidemic in Kasai-Occidental Province that resulted in dozens of cases and fatalities and was caused by the highly virulent Zaire ebolavirus.
  • C. 2014–2016 West Africa Ebola outbreak
    The 2014–2016 West Africa Ebola outbreak was the largest and deadliest Ebola epidemic in history, primarily affecting Guinea, Liberia, and Sierra Leone and prompting a major international public health emergency response.
  • D. 1995 Kikwit Ebola outbreak
    The 1995 Kikwit Ebola outbreak was a major epidemic of Ebola virus disease in Kikwit, Zaire (now the Democratic Republic of the Congo), that caused hundreds of cases and deaths and became a key event in understanding and responding to Ebola.
  • E. Ministry of Health of the DRC Ebola response
    The Ministry of Health of the DRC Ebola response is the national public health authority’s coordinated program to detect, contain, and manage Ebola outbreaks across the Democratic Republic of the Congo.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: publicHealthEmergency
Context triple: [Kalunguta, publicHealthEmergency, Kivu Ebola epidemic]
  • A. publicHealthEmergencyOfInternationalConcern chosen
    Indicates that a health event is so serious, sudden, unusual, or unexpected that it poses a public health risk to other countries and may require a coordinated international response.
  • B. publicHealthResponse
    Indicates actions and measures taken by authorities or organizations to prevent, control, or mitigate health threats within a population.
  • C. epidemicControlActivities
    Indicates actions or measures undertaken to prevent, contain, or mitigate the spread and impact of an epidemic.
  • D. worldHealthOrganizationStatus
    Indicates the relationship between an entity and its classification or status as defined by the World Health Organization (WHO), such as recognition, designation, or official standing.
  • E. epidemicImpact
    Indicates the extent and nature of how an epidemic affects entities, such as populations, regions, or systems.
  • F. None of above.

Provenance (4 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_69bd4441d1648190a54a533895041987 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd7d5a23908190a24e79d1b29d6fcf completed March 20, 2026, 5:01 p.m.
NED1 Entity disambiguation (via context triple) batch_69becfcf12448190a196e9397958fbba completed March 21, 2026, 5:05 p.m.
PD Predicate disambiguation batch_69bd77aa68b88190a50dd736a72d2901 completed March 20, 2026, 4:36 p.m.
Created at: March 20, 2026, 1:41 p.m.