Triple

T9035611
Position Surface form Disambiguated ID Type / Status
Subject Sikasso E216484 entity
Predicate climateClassification P193 FINISHED
Object Köppen Aw E97834 NE 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: Köppen Aw | Statement: [Sikasso, climateClassification, Köppen Aw]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Köppen Aw
Context triple: [Sikasso, climateClassification, Köppen Aw]
  • A. Köppen Aw chosen
    Köppen Aw is a tropical savanna climate type characterized by consistently warm temperatures and a pronounced dry season.
  • B. Köppen Cwa
    Köppen Cwa is a humid subtropical climate type characterized by hot, wet summers and mild, dry winters, typically influenced by monsoonal patterns.
  • C. Köppen Dwa
    Köppen Dwa is a humid continental climate subtype characterized by hot, wet summers and cold, dry winters with a pronounced monsoonal influence.
  • D. Köppen BWh
    Köppen BWh is the hot desert climate subtype characterized by extremely low annual precipitation, very high temperatures, and abundant sunshine, typical of the world’s driest desert regions.
  • E. Köppen BWk
    Köppen BWk is a cold semi-arid (steppe) climate type characterized by low precipitation, hot summers, and cold winters, typically found in continental interior regions.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69ca83d10b608190b2b2f8e0a7faaf14 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cc6ac0b00c8190a7250b86bb7cc276 completed April 1, 2026, 12:45 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfdbd1cd688190a4456f242e6d3ddf completed April 3, 2026, 3:25 p.m.
Created at: March 30, 2026, 7:08 p.m.