Triple

T1837933
Position Surface form Disambiguated ID Type / Status
Subject Rioni E41107 entity
Predicate emptiesNear P408 FINISHED
Object Poti seaport E204190 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 seaport | Statement: [Rioni, emptiesNear, Poti seaport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Poti seaport
Context triple: [Rioni, emptiesNear, Poti seaport]
  • A. Poti
    Poti is a port city on Georgia’s Black Sea coast that serves as a major maritime and transportation hub for the country.
  • B. Batumi Sea Port
    Batumi Sea Port is a major Black Sea maritime hub in Georgia, serving as a key gateway for regional trade and transportation.
  • C. Black Sea port of Poti chosen
    The Black Sea port of Poti is a major Georgian seaport and transport hub that serves as a key gateway for maritime trade between the Caucasus region and international markets.
  • D. 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.
  • E. Sukhumi
    Sukhumi is a Black Sea coastal city that serves as the de facto capital and largest urban center of the disputed region of Abkhazia.
  • 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_69a88647f9388190909bc36e795bdaec completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69abb039cb588190b2626245a7f0bd67 completed March 7, 2026, 4:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69adfba141fc819084cf5903eced2326 completed March 8, 2026, 10:43 p.m.
Created at: March 4, 2026, 7:33 p.m.