Triple

T1824285
Position Surface form Disambiguated ID Type / Status
Subject Tbilisi–Poti railway line E40614 entity
Predicate hasEndpointCity P26386 FINISHED
Object Poti E41301 NE FINISHED

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: Poti | Statement: [Tbilisi–Poti railway line, hasEndpointCity, Poti]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Poti
Context triple: [Tbilisi–Poti railway line, hasEndpointCity, Poti]
  • A. Poti chosen
    Poti is a port city on Georgia’s Black Sea coast that serves as a major maritime and transportation hub for the country.
  • B. Saranda
    Saranda is a coastal city in southern Albania on the Ionian Sea, known for its strategic harbor and role in regional military and maritime history.
  • C. Batumi
    Batumi is a major Black Sea resort city in southwestern Georgia known for its beaches, modern skyline, and role as a regional economic and cultural hub.
  • D. Durrës
    Durrës is a major port city on the Adriatic coast of Albania, historically significant as a strategic maritime gateway and one of the country’s oldest urban centers.
  • E. Vlora
    Vlora is a major coastal city and seaport in southwestern Albania, strategically located on the Adriatic Sea.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69a8864644bc8190b2358ab897194ac1 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa662e0308819081c75ebbdfbf491e completed March 6, 2026, 5:29 a.m.
NED1 Entity disambiguation (via context triple) batch_69addf42de6081908182cd3bda9c69e9 completed March 8, 2026, 8:42 p.m.
Created at: March 4, 2026, 7:32 p.m.