Triple

T6494991
Position Surface form Disambiguated ID Type / Status
Subject Zemun E148133 entity
Predicate historicalRegion P915 FINISHED
Object Srem
Srem is a historical region in the Pannonian Plain, spanning parts of present-day Serbia and Croatia between the Danube and Sava rivers.
E598136 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: Srem | Statement: [Zemun, historicalRegion, Srem]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Srem
Context triple: [Zemun, historicalRegion, Srem]
  • A. Smiljan
    Smiljan is a village in modern-day Croatia best known as the birthplace of inventor Nikola Tesla.
  • B. Posavina
    Posavina is a historical and geographical region along the Sava River in Bosnia and Herzegovina and neighboring countries, known for its fertile plains and mixed ethnic communities.
  • C. Baranja
    Baranja is a historical and geographical region in eastern Croatia and southern Hungary, known for its fertile plains, vineyards, and multicultural heritage.
  • D. Ilijaš
    Ilijaš is a town and municipality in central Bosnia and Herzegovina, situated northwest of Sarajevo and known for its industrial heritage and surrounding hilly landscape.
  • E. Hrvatsko Zagorje
    Hrvatsko Zagorje is a hilly cultural and historical region in northern Croatia, known for its picturesque villages, thermal spas, and traditional rural architecture.
  • 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: Srem
Triple: [Zemun, historicalRegion, Srem]
Generated description
Srem is a historical region in the Pannonian Plain, spanning parts of present-day Serbia and Croatia between the Danube and Sava rivers.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Srem
Target entity description: Srem is a historical region in the Pannonian Plain, spanning parts of present-day Serbia and Croatia between the Danube and Sava rivers.
  • A. Smiljan
    Smiljan is a village in modern-day Croatia best known as the birthplace of inventor Nikola Tesla.
  • B. Posavina
    Posavina is a historical and geographical region along the Sava River in Bosnia and Herzegovina and neighboring countries, known for its fertile plains and mixed ethnic communities.
  • C. Baranja
    Baranja is a historical and geographical region in eastern Croatia and southern Hungary, known for its fertile plains, vineyards, and multicultural heritage.
  • D. Ilijaš
    Ilijaš is a town and municipality in central Bosnia and Herzegovina, situated northwest of Sarajevo and known for its industrial heritage and surrounding hilly landscape.
  • E. Hrvatsko Zagorje
    Hrvatsko Zagorje is a hilly cultural and historical region in northern Croatia, known for its picturesque villages, thermal spas, and traditional rural architecture.
  • 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_69c009088f3081909cd467b05919de30 completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c06ab958808190bd85e007e925ffc4 completed March 22, 2026, 10:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69c669e216608190af64f8e61ddf0feb completed March 27, 2026, 11:28 a.m.
NEDg Description generation batch_69c66a76cb308190bdc5de9171b6d73d completed March 27, 2026, 11:31 a.m.
NED2 Entity disambiguation (via description) batch_69c66aeaeb4081908cf3fd847e5e0de9 completed March 27, 2026, 11:32 a.m.
Created at: March 22, 2026, 4:53 p.m.