Triple

T13646959
Position Surface form Disambiguated ID Type / Status
Subject Herzegovina E326127 entity
Predicate hasCity P316 FINISHED
Object Ravno
Ravno is a small town and municipality in southern Bosnia and Herzegovina, known as one of the country's southernmost settlements and a gateway to the Popovo Polje region.
 E1053762 NE FINISHED

How this triple was built (4 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: Ravno | Statement: [Herzegovina, hasCity, Ravno]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Ravno
Context triple: [Herzegovina, hasCity, Ravno]
  • A. Rovno
    Rovno is the former Russian and Polish name for the Ukrainian city now known as Rivne, a regional center in western Ukraine.
  • B. Równe
    Równe is a town in western Poland that serves as a twin town to Głogów.
  • C. Rupea
    Rupea is a small historic town in central Romania, known for its medieval hilltop fortress and location within Brașov County in Transylvania.
  • D. Razov
    Razov is a surname most notably associated with Ante Razov, a former American professional soccer player and prolific Major League Soccer goal scorer.
  • E. Zau
    Zau is an ancient city, historically known as Sais, that served as an important religious and political center in Egypt’s Nile Delta.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Ravno
Triple: [Herzegovina, hasCity, Ravno]
Generated description
Ravno is a small town and municipality in southern Bosnia and Herzegovina, known as one of the country's southernmost settlements and a gateway to the Popovo Polje region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Ravno
Target entity description: Ravno is a small town and municipality in southern Bosnia and Herzegovina, known as one of the country's southernmost settlements and a gateway to the Popovo Polje region.
  • A. Rovno
    Rovno is the former Russian and Polish name for the Ukrainian city now known as Rivne, a regional center in western Ukraine.
  • B. Równe
    Równe is a town in western Poland that serves as a twin town to Głogów.
  • C. Rupea
    Rupea is a small historic town in central Romania, known for its medieval hilltop fortress and location within Brașov County in Transylvania.
  • D. Razov
    Razov is a surname most notably associated with Ante Razov, a former American professional soccer player and prolific Major League Soccer goal scorer.
  • E. Zau
    Zau is an ancient city, historically known as Sais, that served as an important religious and political center in Egypt’s Nile Delta.
  • F. None of above. chosen

Provenance (5 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_69d8076beddc8190a53156f5bea77f5e completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbc6073e888190965456a639839749 completed April 12, 2026, 4:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69f78af948408190bca7f2e46863391e completed May 3, 2026, 5:50 p.m.
NEDg Description generation batch_69f78bd52b748190ab483ec7634a6549 completed May 3, 2026, 5:54 p.m.
NED2 Entity disambiguation (via description) batch_69f78d277c5c8190970cb3cd0fd32905 completed May 3, 2026, 6 p.m.
Created at: April 9, 2026, 9:52 p.m.