Triple

T19647152
Position Surface form Disambiguated ID Type / Status
Subject Keşan campus E471703 entity
Predicate regionServed P82 FINISHED
Object Keşan district 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: Keşan district | Statement: [Keşan campus, regionServed, Keşan district]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Keşan district
Context triple: [Keşan campus, regionServed, Keşan district]
  • A. Keşan district chosen
    Keşan district is an administrative region in Edirne Province in northwestern Turkey, known for its strategic location near the Aegean Sea and the Greek border.
  • B. Khojavend District
    Khojavend District is an administrative region of Azerbaijan located in the disputed Nagorno-Karabakh area, known for its strategic significance and involvement in the Armenian–Azerbaijani conflict.
  • C. Bekabad District
    Bekabad District is an administrative district in eastern Uzbekistan known for its industrial town of Bekabad and its location within the Tashkent Region.
  • D. Zangilan District
    Zangilan District is a region in southwestern Azerbaijan, located near the borders with Armenia and Iran and known for its strategic position in the South Caucasus.
  • E. Ziarat District
    Ziarat District is a mountainous administrative region in northeastern Balochistan, Pakistan, known for its juniper forests and the historic Ziarat Residency.
  • 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_69d8e51395348190ac1416d46dfc6db0 completed April 10, 2026, 11:54 a.m.
NER Named-entity recognition batch_69e64125dd9481908a891c71c975a964 completed April 20, 2026, 3:07 p.m.
Created at: April 10, 2026, 1:44 p.m.