Triple

T12630521
Position Surface form Disambiguated ID Type / Status
Subject Battle of Mariupol (2014) E301626 entity
Predicate belligerentSide P375 FINISHED
Object Ukraine E14078 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: Ukraine | Statement: [Battle of Mariupol (2014), belligerentSide, Ukraine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ukraine
Context triple: [Battle of Mariupol (2014), belligerentSide, Ukraine]
  • A. Ukraine chosen
    Ukraine is a large Eastern European country known for its fertile plains, strategic geopolitical position between Russia and the European Union, and its complex 20th- and 21st-century history marked by independence struggles and ongoing conflict.
  • B. Ukrainka
    Ukrainka is a small city in northern Ukraine situated along the Dnipro River within the Kyiv metropolitan area.
  • C. Ukraine and Moldova
    Ukraine and Moldova are neighboring Eastern European countries that share historical, cultural, and economic ties as well as a long land border.
  • D. Ukraine–Poland
    Ukraine–Poland refers to the shared border area and broader historical-cultural region linking Ukraine and Poland in Eastern Europe.
  • E. Romania and Ukraine
    Romania and Ukraine are neighboring Eastern European countries that share both land and river borders, including stretches along the Prut River.
  • 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_69d7bdeaf49c8190b13800111fa77ea3 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d9610ce9e48190a496824002c0d2be completed April 10, 2026, 8:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6719676d48190bcc9d7ccbde2605e completed May 2, 2026, 9:50 p.m.
Created at: April 9, 2026, 5:15 p.m.