Triple

T16991079
Position Surface form Disambiguated ID Type / Status
Subject Split-Dalmatia County E412194 entity
Predicate containsRiver P165 FINISHED
Object Jadro
Jadro is a short karst river in Croatia known for supplying drinking water to the city of Split and its surroundings.
E1244421 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: Jadro | Statement: [Split-Dalmatia County, containsRiver, Jadro]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jadro
Context triple: [Split-Dalmatia County, containsRiver, Jadro]
  • A. Nuklo
    Nuklo is a Marvel Comics superhuman character known as the radioactive, energy-emitting son of the speedster Whizzer.
  • B. Paks
    Paks is a Hungarian town best known for hosting the country's only nuclear power plant, a key source of its electricity.
  • C. Zirc
    Zirc is a small Hungarian town in Veszprém County known for its historic Cistercian Abbey and scenic location in the Bakony Mountains.
  • D. Obninsk
    Obninsk is a Russian city best known as the site of the world’s first grid-connected nuclear power plant and an important center for nuclear and scientific research.
  • E. Slavutych
    Slavutych is a planned Ukrainian city built after the Chernobyl disaster to house evacuated workers and their families, known for its unique multinational architectural design.
  • 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: Jadro
Triple: [Split-Dalmatia County, containsRiver, Jadro]
Generated description
Jadro is a short karst river in Croatia known for supplying drinking water to the city of Split and its surroundings.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Jadro
Target entity description: Jadro is a short karst river in Croatia known for supplying drinking water to the city of Split and its surroundings.
  • A. Nuklo
    Nuklo is a Marvel Comics superhuman character known as the radioactive, energy-emitting son of the speedster Whizzer.
  • B. Paks
    Paks is a Hungarian town best known for hosting the country's only nuclear power plant, a key source of its electricity.
  • C. Zirc
    Zirc is a small Hungarian town in Veszprém County known for its historic Cistercian Abbey and scenic location in the Bakony Mountains.
  • D. Obninsk
    Obninsk is a Russian city best known as the site of the world’s first grid-connected nuclear power plant and an important center for nuclear and scientific research.
  • E. Slavutych
    Slavutych is a planned Ukrainian city built after the Chernobyl disaster to house evacuated workers and their families, known for its unique multinational architectural design.
  • 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_69d886cb581c8190ab05f4b429c9cd85 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d280e3348190a27bd5dc7cf87c0e completed April 18, 2026, 6:50 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00dc14d5688190945f7ae72f724922 completed May 10, 2026, 7:27 p.m.
NEDg Description generation batch_6a0114d5aeb0819086f1a5d279ac0d0f completed May 10, 2026, 11:29 p.m.
NED2 Entity disambiguation (via description) batch_6a0115c583608190bf07ac205399f253 completed May 10, 2026, 11:33 p.m.
Created at: April 10, 2026, 5:32 a.m.