Triple

T20171396
Position Surface form Disambiguated ID Type / Status
Subject Tbilisi Basin E491966 entity
Predicate contains P35 FINISHED
Object Tbilisi lowland 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: Tbilisi lowland | Statement: [Tbilisi Basin, contains, Tbilisi lowland]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tbilisi lowland
Context triple: [Tbilisi Basin, contains, Tbilisi lowland]
  • A. Tbilisi Basin chosen
    The Tbilisi Basin is a geological depression in eastern Georgia that forms the broader lowland area surrounding the country’s capital, Tbilisi.
  • B. Martvili plateau
    Martvili plateau is a highland area in western Georgia known for its scenic landscapes and historical sites, including the medieval Martvili Monastery.
  • C. Samtskhe-Javakheti
    Samtskhe-Javakheti is a historical and cultural region in southern Georgia known for its mountainous landscapes, medieval fortresses, and ethnically diverse population.
  • D. Tusheti
    Tusheti is a remote mountainous region in northeast Georgia known for its medieval villages, pastoral culture, and well-preserved traditions of the local highland communities.
  • E. Guria
    Guria is a historical region in western Georgia known for its Black Sea coastline, rich folk traditions, and distinctive polyphonic singing.
  • 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_69da6266c6888190bc1a3ecf24814d34 completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e66848ae3c8190aa5fde66da35a89a completed April 20, 2026, 5:54 p.m.
Created at: April 11, 2026, 11:35 p.m.