Triple

T2942044
Position Surface form Disambiguated ID Type / Status
Subject Dečani Monastery E79408 entity
Predicate locatedIn P40 FINISHED
Object Metohija
Metohija is a historical region in western Kosovo known for its fertile plains and numerous medieval Serbian Orthodox monasteries.
E311399 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: Metohija | Statement: [Dečani Monastery, locatedIn, Metohija]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Metohija
Context triple: [Dečani Monastery, locatedIn, Metohija]
  • A. Morača
    Morača is a major river in Montenegro that flows through the capital city of Podgorica before emptying into Lake Skadar.
  • B. Kamenitsa
    Kamenitsa is a prominent mountain peak in Bulgaria’s Pirin range, known for its rugged alpine terrain and scenic hiking routes.
  • C. Sagarejo
    Sagarejo is a town in eastern Georgia that serves as an important local center in the Kakheti wine-producing region.
  • D. Midžor
    Midžor is a prominent mountain peak in the Balkan range on the Serbia–Bulgaria border, known for its scenic alpine landscapes and popularity among hikers.
  • E. Rakovica
    Rakovica is a suburban municipality of Belgrade, Serbia, known for its mixed residential and industrial areas and proximity to forested landscapes.
  • 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: Metohija
Triple: [Dečani Monastery, locatedIn, Metohija]
Generated description
Metohija is a historical region in western Kosovo known for its fertile plains and numerous medieval Serbian Orthodox monasteries.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Metohija
Target entity description: Metohija is a historical region in western Kosovo known for its fertile plains and numerous medieval Serbian Orthodox monasteries.
  • A. Morača
    Morača is a major river in Montenegro that flows through the capital city of Podgorica before emptying into Lake Skadar.
  • B. Kamenitsa
    Kamenitsa is a prominent mountain peak in Bulgaria’s Pirin range, known for its rugged alpine terrain and scenic hiking routes.
  • C. Sagarejo
    Sagarejo is a town in eastern Georgia that serves as an important local center in the Kakheti wine-producing region.
  • D. Midžor
    Midžor is a prominent mountain peak in the Balkan range on the Serbia–Bulgaria border, known for its scenic alpine landscapes and popularity among hikers.
  • E. Rakovica
    Rakovica is a suburban municipality of Belgrade, Serbia, known for its mixed residential and industrial areas and proximity to forested landscapes.
  • 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_69ad8b1089588190b74d9e2505e45762 completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad9870e5d08190b3b277ba823fe6a1 completed March 8, 2026, 3:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69b08689ec3481909d9f039069ff19c7 completed March 10, 2026, 9 p.m.
NEDg Description generation batch_69b0d241c7088190b440a47f4af54fbb completed March 11, 2026, 2:24 a.m.
NED2 Entity disambiguation (via description) batch_69b0d6466e848190bea4215cc9d358c7 completed March 11, 2026, 2:41 a.m.
Created at: March 8, 2026, 2:56 p.m.