Triple

T15557986
Position Surface form Disambiguated ID Type / Status
Subject Vrbas E370919 entity
Predicate hasTributary P415 FINISHED
Object Pliva
Pliva is a river in western Bosnia and Herzegovina known for its scenic waterfalls and lakes near the town of Jajce.
 E1163385 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: Pliva | Statement: [Vrbas, hasTributary, Pliva]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Pliva
Context triple: [Vrbas, hasTributary, Pliva]
  • A. Sandoz
    Sandoz is a historic Swiss pharmaceutical company best known as a predecessor of Novartis and a major player in generic medicines.
  • B. Roche
    Roche is a common surname of French origin borne by various notable individuals across fields such as architecture, politics, and the arts.
  • C. Roche
    Roche is a major Swiss multinational healthcare company and one of the world’s leading pharmaceutical and diagnostics firms.
  • D. Bayer
    Bayer is a major German multinational pharmaceutical and life sciences company known for products such as aspirin and its work in healthcare and agriculture.
  • E. Pharmacia
    Pharmacia was a major pharmaceutical company known for its global drug development and manufacturing operations before ultimately becoming part of Pfizer.
  • 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: Pliva
Triple: [Vrbas, hasTributary, Pliva]
Generated description
Pliva is a river in western Bosnia and Herzegovina known for its scenic waterfalls and lakes near the town of Jajce.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Pliva
Target entity description: Pliva is a river in western Bosnia and Herzegovina known for its scenic waterfalls and lakes near the town of Jajce.
  • A. Sandoz
    Sandoz is a historic Swiss pharmaceutical company best known as a predecessor of Novartis and a major player in generic medicines.
  • B. Roche
    Roche is a common surname of French origin borne by various notable individuals across fields such as architecture, politics, and the arts.
  • C. Roche
    Roche is a major Swiss multinational healthcare company and one of the world’s leading pharmaceutical and diagnostics firms.
  • D. Bayer
    Bayer is a major German multinational pharmaceutical and life sciences company known for products such as aspirin and its work in healthcare and agriculture.
  • E. Pharmacia
    Pharmacia was a major pharmaceutical company known for its global drug development and manufacturing operations before ultimately becoming part of Pfizer.
  • 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_69d85cc6cf40819091f4a5facee1ebe6 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04dda3ab88190ab383333ce69fe8f completed April 16, 2026, 2:47 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff456635588190a2473bcff3ae4a53 completed May 9, 2026, 2:32 p.m.
NEDg Description generation batch_69ff46f44b2c81909f65f0ab455c6549 completed May 9, 2026, 2:38 p.m.
NED2 Entity disambiguation (via description) batch_69ff477a63b48190a453cf669dfda228 completed May 9, 2026, 2:40 p.m.
Created at: April 10, 2026, 4:09 a.m.