Triple

T19926653
Position Surface form Disambiguated ID Type / Status
Subject თავისუფლების მოედანი E478940 entity
Predicate connectsTo P845 FINISHED
Object Leselidze Street 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: Leselidze Street | Statement: [თავისუფლების მოედანი, connectsTo, Leselidze Street]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Leselidze Street
Context triple: [თავისუფლების მოედანი, connectsTo, Leselidze Street]
  • A. Leselidze Street chosen
    Leselidze Street is a historic and popular thoroughfare in Tbilisi’s Old Town, known for its shops, cafes, and traditional architecture.
  • B. Tabukashvili Street
    Tabukashvili Street is a central street in Tbilisi, Georgia, known for its proximity to Freedom Square and its mix of historic and cultural landmarks.
  • C. Merab Kostava Street
    Merab Kostava Street is a major thoroughfare in Tbilisi, Georgia, known for its central location and significant cultural and institutional landmarks.
  • D. Ibraimov Street
    Ibraimov Street is a notable thoroughfare in Bishkek, Kyrgyzstan, known for hosting important city landmarks such as Victory Square.
  • E. Udaltsova Street
    Udaltsova Street is a street in Moscow, Russia, located near Prospekt Vernadskogo metro station and forming part of the city’s southwestern residential and transport network.
  • 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.