Triple

T4537129
Position Surface form Disambiguated ID Type / Status
Subject Bar E107433 entity
Predicate nearbyCity P350 FINISHED
Object Ulcinj E142587 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: Ulcinj | Statement: [Bar, nearbyCity, Ulcinj]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ulcinj
Context triple: [Bar, nearbyCity, Ulcinj]
  • A. 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.
  • B. Vlora
    Vlora is a major coastal city and seaport in southwestern Albania, strategically located on the Adriatic Sea.
  • C. Pogradec
    Pogradec is a town in southeastern Albania known as a lakeside resort and cultural center on the shores of Lake Ohrid.
  • D. Herceg Novi chosen
    Herceg Novi is a coastal town in western Montenegro known for its historic old town, fortresses, and scenic location at the entrance to the Bay of Kotor.
  • E. Makarska
    Makarska is a coastal town and popular tourist resort on the Adriatic Sea in southern Croatia, known for its beaches and the nearby Biokovo mountain range.
  • 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_69bd43f922788190b7edfa294e39b178 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd57b78b8481909d79131723d4be22 completed March 20, 2026, 2:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdacfb2ba48190b7f1b23785e9d030 completed March 20, 2026, 8:24 p.m.
Created at: March 20, 2026, 1:04 p.m.