Triple

T34865309
Position Surface form Disambiguated ID Type / Status
Subject Great Lakes refugee crises E1004991 entity
Predicate linkedConflict P196999 FINISHED
Object Rwandan genocide 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: Rwandan genocide | Statement: [Great Lakes refugee crises, linkedConflict, Rwandan genocide]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: linkedConflict
Context triple: [Great Lakes refugee crises, linkedConflict, Rwandan genocide]
  • A. reportedConflict
    Indicates that one party has formally reported the existence of a conflict involving another party or situation.
  • B. ledToConflict
    Indicates that one event, action, or condition caused or significantly contributed to the emergence or escalation of a conflict between parties.
  • C. holderConflict
    Indicates a relationship where the current holder or possessor of something is in conflict or dispute over that holding, such as ownership, control, or rights.
  • D. captureConflict
    Indicates that one entity records, represents, or encapsulates a conflict involving another entity or between multiple entities.
  • E. conflictWith
    Indicates that two entities are in opposition or disagreement, such that their goals, actions, or states are incompatible or interfere with each other.
  • F. None of above. chosen

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_69f76dbb678081909a247b9b5e1a73ac completed May 3, 2026, 3:46 p.m.
NER Named-entity recognition batch_69fe72dca2f08190beff17de3d2aada6 completed May 8, 2026, 11:33 p.m.
PD Predicate disambiguation batch_69fe70bca8d08190b810e1e616ceac44 completed May 8, 2026, 11:24 p.m.
PDg Predicate description generation batch_69fe72db8810819089e397961b8ead7a completed May 8, 2026, 11:33 p.m.
Created at: May 3, 2026, 4 p.m.