Triple

T13357896
Position Surface form Disambiguated ID Type / Status
Subject Stefan Uroš III Dečanski E318741 entity
Predicate child P120 FINISHED
Object Dušica
Dušica was a medieval Serbian princess, the daughter of King Stefan Uroš III Dečanski of Serbia.
 E1056502 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: Dušica | Statement: [Stefan Uroš III Dečanski, child, Dušica]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Dušica
Context triple: [Stefan Uroš III Dečanski, child, Dušica]
  • A. Dudinka
    Dudinka is a remote Arctic port town in northern Siberia, Russia, serving as a key shipping hub on the Yenisei River and gateway to the Norilsk industrial region.
  • B. Morača
    Morača is a major river in Montenegro that flows through the capital city of Podgorica before emptying into Lake Skadar.
  • C. Vranje
    Vranje is a historic city in southern Serbia known for its Ottoman-era architecture, cultural heritage, and role as an administrative and economic center of the region.
  • D. Dobruška
    Dobruška is a small historic town in the Hradec Králové Region of the Czech Republic, known for its preserved architecture and regional cultural heritage.
  • E. Fažana
    Fažana is a coastal town in Croatia’s Istria region, known for its fishing heritage, tourism, and historical ties to the Istriot language.
  • 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: Dušica
Triple: [Stefan Uroš III Dečanski, child, Dušica]
Generated description
Dušica was a medieval Serbian princess, the daughter of King Stefan Uroš III Dečanski of Serbia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Dušica
Target entity description: Dušica was a medieval Serbian princess, the daughter of King Stefan Uroš III Dečanski of Serbia.
  • A. Dudinka
    Dudinka is a remote Arctic port town in northern Siberia, Russia, serving as a key shipping hub on the Yenisei River and gateway to the Norilsk industrial region.
  • B. Morača
    Morača is a major river in Montenegro that flows through the capital city of Podgorica before emptying into Lake Skadar.
  • C. Vranje
    Vranje is a historic city in southern Serbia known for its Ottoman-era architecture, cultural heritage, and role as an administrative and economic center of the region.
  • D. Dobruška
    Dobruška is a small historic town in the Hradec Králové Region of the Czech Republic, known for its preserved architecture and regional cultural heritage.
  • E. Fažana
    Fažana is a coastal town in Croatia’s Istria region, known for its fishing heritage, tourism, and historical ties to the Istriot language.
  • 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_69d806b7bbac8190b85278c87fa7aff3 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69da62887e588190bd7241c720a112a2 completed April 11, 2026, 3:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69f79d360c60819086a8168bdc092e1c completed May 3, 2026, 7:08 p.m.
NEDg Description generation batch_69f79db9710c8190969503e28e2cda46 completed May 3, 2026, 7:10 p.m.
NED2 Entity disambiguation (via description) batch_69f79e1dcc9481908a22dfd74445bc89 completed May 3, 2026, 7:12 p.m.
Created at: April 9, 2026, 9:32 p.m.