Triple

T25563320
Position Surface form Disambiguated ID Type / Status
Subject Operation Medak Pocket E640771 entity
Predicate peacekeepingForce P76177 FINISHED
Object UNPROFOR NE NERFINISHED

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: UNPROFOR | Statement: [Operation Medak Pocket, peacekeepingForce, UNPROFOR]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: peacekeepingForce
Context triple: [Operation Medak Pocket, peacekeepingForce, UNPROFOR]
  • A. peacekeepingContingent chosen
    Indicates that a group of personnel or forces is deployed with the mandate to help maintain or restore peace between parties in a conflict or post-conflict situation.
  • B. peacekeepingMissionName
    Indicates the specific name assigned to a particular peacekeeping mission in which an entity is involved or referenced.
  • C. peacekeepingModel
    Indicates a model or framework designed to guide, structure, or simulate peacekeeping actions and relationships between involved parties.
  • D. peacekeepingPartner
    Indicates a cooperative relationship in which entities jointly participate in or support peacekeeping activities or missions.
  • E. hasPeacekeepingComponent
    Indicates that something includes, involves, or is associated with a peacekeeping-related element, unit, or function.
  • 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_69e75dc1beb08190bac7d76b8d6e7bc4 completed April 21, 2026, 11:21 a.m.
NER Named-entity recognition batch_69f5f8fa9fa0819098761026a7f9353d completed May 2, 2026, 1:15 p.m.
PD Predicate disambiguation batch_69f468421ba08190880eac99135e5970 completed May 1, 2026, 8:45 a.m.
Created at: April 21, 2026, 3:47 p.m.