Triple

T13550794
Position Surface form Disambiguated ID Type / Status
Subject Lesce E323637 entity
Predicate locatedOnRiver P165 FINISHED
Object Sava Dolinka
Sava Dolinka is a river in northwestern Slovenia that forms one of the two headwaters of the Sava, the longest river in the country.
 E1057152 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: Sava Dolinka | Statement: [Lesce, locatedOnRiver, Sava Dolinka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sava Dolinka
Context triple: [Lesce, locatedOnRiver, Sava Dolinka]
  • A. Savski Venac
    Savski Venac is a central urban municipality of Belgrade, Serbia, known for its government institutions, major transport hubs, and historic neighborhoods.
  • B. Vrbnik
    Vrbnik is a historic coastal town on the Croatian island of Krk, known for its clifftop old town, narrow streets, and production of the Žlahtina white wine.
  • C. Ojstrica
    Ojstrica is a prominent mountain peak in northern Slovenia, known for its steep limestone walls and scenic views within the Kamnik–Savinja Alps.
  • D. Vrlika
    Vrlika is a small historic town in inland Dalmatia, Croatia, known for its scenic setting near Lake Peruća and the Dinara mountain range.
  • E. Ravni Žakan
    Ravni Žakan is one of the islands within Croatia’s Kornati National Park, known for its rugged coastline and clear Adriatic waters.
  • 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: Sava Dolinka
Triple: [Lesce, locatedOnRiver, Sava Dolinka]
Generated description
Sava Dolinka is a river in northwestern Slovenia that forms one of the two headwaters of the Sava, the longest river in the country.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sava Dolinka
Target entity description: Sava Dolinka is a river in northwestern Slovenia that forms one of the two headwaters of the Sava, the longest river in the country.
  • A. Savski Venac
    Savski Venac is a central urban municipality of Belgrade, Serbia, known for its government institutions, major transport hubs, and historic neighborhoods.
  • B. Vrbnik
    Vrbnik is a historic coastal town on the Croatian island of Krk, known for its clifftop old town, narrow streets, and production of the Žlahtina white wine.
  • C. Ojstrica
    Ojstrica is a prominent mountain peak in northern Slovenia, known for its steep limestone walls and scenic views within the Kamnik–Savinja Alps.
  • D. Vrlika
    Vrlika is a small historic town in inland Dalmatia, Croatia, known for its scenic setting near Lake Peruća and the Dinara mountain range.
  • E. Ravni Žakan
    Ravni Žakan is one of the islands within Croatia’s Kornati National Park, known for its rugged coastline and clear Adriatic waters.
  • 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_69d8076776248190bdf0d4fa1f85a5fc completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbaff0a6548190b8cde5084cef0061 completed April 12, 2026, 2:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69f79d3d860c8190a166666a20971de7 completed May 3, 2026, 7:08 p.m.
NEDg Description generation batch_69f79f9b643881908fdd9e1fed8e2af4 completed May 3, 2026, 7:18 p.m.
NED2 Entity disambiguation (via description) batch_69f7a01ccda881909a76cec423e05f66 completed May 3, 2026, 7:21 p.m.
Created at: April 9, 2026, 9:46 p.m.