Triple

T21275005
Position Surface form Disambiguated ID Type / Status
Subject Southwestern Greece E524365 entity
Predicate containsCity P294 FINISHED
Object Krestena 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: Krestena | Statement: [Southwestern Greece, containsCity, Krestena]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Krestena
Context triple: [Southwestern Greece, containsCity, Krestena]
  • A. Krestena chosen
    Krestena is a small town in western Greece, located in the regional unit of Elis in the Peloponnese.
  • B. Kresta
    Kresta is a settlement located on the shore of Kresta Bay in the Russian Far East.
  • C. Kerkini
    Kerkini is an alternative name for the Belasica mountain range in the Balkans, which spans parts of Greece, North Macedonia, and Bulgaria.
  • D. Johannitsa
    Johannitsa was a medieval Bulgarian ruler better known as Kaloyan, the tsar who significantly expanded the Second Bulgarian Empire in the early 13th century.
  • E. Krestinsky
    Krestinsky is a Russian surname most notably associated with Nikolai Krestinsky, a Soviet politician and diplomat active during the early years of the USSR.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b516293c819089458ea2ec85f85e completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7365627a081908caea09097cca354 completed April 21, 2026, 8:33 a.m.
Created at: April 16, 2026, 4:01 p.m.