Triple

T16280064
Position Surface form Disambiguated ID Type / Status
Subject Kula E395239 entity
Predicate hasSettlement P1068 FINISHED
Object Sivac
Sivac is a village in the Vojvodina region of northern Serbia, known as one of the settlements within the municipality of Kula.
 E1203491 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: Sivac | Statement: [Kula, hasSettlement, Sivac]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sivac
Context triple: [Kula, hasSettlement, Sivac]
  • A. Sivorg
    Sivorg was a clandestine Norwegian resistance organization during World War II that coordinated civilian opposition and underground activities against the German occupation.
  • B. Varketili
    Varketili is a metro station in Tbilisi, Georgia, serving as a key terminus on the Tbilisi Metro network.
  • C. Gavro
    Gavro is a diminutive or short form of the male given name Gavril, commonly used in some Slavic-speaking regions.
  • D. Pavica
    Pavica is a feminine given name of South Slavic origin, commonly used as a diminutive form of the name Pavao.
  • E. Sancar
    Sancar is the surname of Aziz Sancar, a Turkish-American biochemist and molecular biologist renowned for his Nobel Prize–winning work on DNA repair.
  • 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: Sivac
Triple: [Kula, hasSettlement, Sivac]
Generated description
Sivac is a village in the Vojvodina region of northern Serbia, known as one of the settlements within the municipality of Kula.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sivac
Target entity description: Sivac is a village in the Vojvodina region of northern Serbia, known as one of the settlements within the municipality of Kula.
  • A. Sivorg
    Sivorg was a clandestine Norwegian resistance organization during World War II that coordinated civilian opposition and underground activities against the German occupation.
  • B. Varketili
    Varketili is a metro station in Tbilisi, Georgia, serving as a key terminus on the Tbilisi Metro network.
  • C. Gavro
    Gavro is a diminutive or short form of the male given name Gavril, commonly used in some Slavic-speaking regions.
  • D. Pavica
    Pavica is a feminine given name of South Slavic origin, commonly used as a diminutive form of the name Pavao.
  • E. Sancar
    Sancar is the surname of Aziz Sancar, a Turkish-American biochemist and molecular biologist renowned for his Nobel Prize–winning work on DNA repair.
  • 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_69d87f22c7248190a54c949738441e2e completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e24611926c81909b276ca3f406f15d completed April 17, 2026, 2:39 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0017c48e5c8190a387a4158362417a completed May 10, 2026, 5:29 a.m.
NEDg Description generation batch_6a0018be4b8c8190b68001465b9af949 completed May 10, 2026, 5:33 a.m.
NED2 Entity disambiguation (via description) batch_6a00198af20c819087cfa7d01b3afdec completed May 10, 2026, 5:37 a.m.
Created at: April 10, 2026, 5:05 a.m.