Triple

T9351595
Position Surface form Disambiguated ID Type / Status
Subject South Sudanese Civil War E225030 entity
Predicate refugees P9069 FINISHED
Object over 2 million people fled to neighboring countries — LITERAL FINISHED

How this triple was built (2 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: over 2 million people fled to neighboring countries | Statement: [South Sudanese Civil War, refugees, over 2 million people fled to neighboring countries]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: refugees
Context triple: [South Sudanese Civil War, refugees, over 2 million people fled to neighboring countries]
  • A. refugeeAdministration
    Indicates the management, coordination, or oversight of services, policies, and procedures related to refugees.
  • B. primaryRefugeeGroup
    Indicates that the referenced group is the main or principal group of refugees associated with a particular context, event, or record.
  • C. hasRefugeePopulation chosen
    Indicates that an entity hosts, contains, or is associated with a population of refugees.
  • D. hasRefugeeCamp
    Indicates that a location or entity hosts, contains, or is the site of a refugee camp.
  • E. displacedPeopleEstimate
    Indicates an estimated number of people who have been forced to leave their homes or usual places of residence due to a particular event or situation.
  • F. None of above.

Provenance (3 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_69ca842abfd48190949d71c3b86eeba8 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd4f93a9848190ad2ae24f2aa607d2 completed April 1, 2026, 5:02 p.m.
PD Predicate disambiguation batch_69cc7a68ab9481909f97cb70764697cc completed April 1, 2026, 1:52 a.m.
Created at: March 30, 2026, 7:41 p.m.