Triple

T16668390
Position Surface form Disambiguated ID Type / Status
Subject Khankendi E405041 entity
Predicate hasRoadConnectionTo P11435 FINISHED
Object Barda E1048668 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: Barda | Statement: [Khankendi, hasRoadConnectionTo, Barda]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Barda
Context triple: [Khankendi, hasRoadConnectionTo, Barda]
  • A. Barda chosen
    Barda is a historic city that once served as a major political and cultural center in the region of Arran, in present-day Azerbaijan.
  • B. Bardaï
    Bardaï is a remote oasis town in northern Chad that serves as an important administrative and cultural center in the Tibesti region.
  • C. Barbareta
    Barbareta is a small, privately owned Caribbean island located in Honduras’s Bay Islands archipelago, known for its natural beauty and relative seclusion.
  • D. Satine Kryze
    Satine Kryze is the pacifist Duchess of Mandalore in the Star Wars universe, prominently known for her complex relationship with Jedi Knight Obi-Wan Kenobi during the Clone Wars era.
  • E. Barduelva
    Barduelva is a river in northern Norway flowing through Troms og Finnmark county, including the town of Setermoen.
  • 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_69d8838b5fbc81908c6575c132b82e80 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e37c9e9a208190afab499897ce4361 completed April 18, 2026, 12:44 p.m.
NED1 Entity disambiguation (via context triple) batch_6a008a34852c81908c00ff8e36923cee completed May 10, 2026, 1:37 p.m.
Created at: April 10, 2026, 5:18 a.m.