Triple

T19927147
Position Surface form Disambiguated ID Type / Status
Subject Saburtalo Line E478953 entity
Predicate connects P390 FINISHED
Object central Tbilisi 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: central Tbilisi | Statement: [Saburtalo Line, connects, central Tbilisi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: central Tbilisi
Context triple: [Saburtalo Line, connects, central Tbilisi]
  • A. Old Tbilisi chosen
    Old Tbilisi is the historic core of Georgia’s capital, known for its narrow cobblestone streets, traditional wooden balconies, sulfur baths, and diverse architectural heritage.
  • B. Tbilisi
    Tbilisi is the largest city and cultural, political, and economic center of Georgia, located on the banks of the Kura River in the South Caucasus.
  • C. Marneuli
    Marneuli is a town in southern Georgia known for its ethnically diverse population, particularly its large Azerbaijani community, and its role as an agricultural and regional trade center.
  • D. Mtskheta
    Mtskheta is an ancient town in central Georgia and a UNESCO World Heritage Site, renowned as one of the country’s oldest continuously inhabited cities and a historic center of Georgian Christianity.
  • E. Kabilasi
    Kabilasi is a municipality-level town located in southeastern Nepal’s Madhesh Province, near the border with India.
  • 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_69d8e521855c8190b41871700afc8d6a completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e659ca52c881908dc8053bf61be4c4 completed April 20, 2026, 4:52 p.m.
Created at: April 10, 2026, 1:53 p.m.