Triple

T17027288
Position Surface form Disambiguated ID Type / Status
Subject Kovin municipality E413098 entity
Predicate containsSettlement P847 FINISHED
Object Šumarak
Šumarak is a small settlement located within the municipality of Kovin in Serbia, known for its rural character and proximity to the Danube plain.
E1246491 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: Šumarak | Statement: [Kovin municipality, containsSettlement, Šumarak]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Šumarak
Context triple: [Kovin municipality, containsSettlement, Šumarak]
  • A. Marsum
    Marsum is a small village in the northern Netherlands, located in the province of Groningen within the municipality of Eemsdelta.
  • B. Al Jumum
    Al Jumum is a town and governorate in western Saudi Arabia, situated near the holy city of Mecca in the Makkah administrative region.
  • C. Shum
    Shum is a Chinese-origin surname borne by various notable individuals, including actors, politicians, and academics in the Chinese diaspora.
  • D. Shimsha
    Shimsha is a river in southern India that flows through Karnataka and is known for its waterfalls and contribution to the Kaveri river system.
  • E. Shalim
    Shalim is a deity from ancient Canaanite religion, commonly associated with dusk or the setting sun.
  • 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: Šumarak
Triple: [Kovin municipality, containsSettlement, Šumarak]
Generated description
Šumarak is a small settlement located within the municipality of Kovin in Serbia, known for its rural character and proximity to the Danube plain.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Šumarak
Target entity description: Šumarak is a small settlement located within the municipality of Kovin in Serbia, known for its rural character and proximity to the Danube plain.
  • A. Marsum
    Marsum is a small village in the northern Netherlands, located in the province of Groningen within the municipality of Eemsdelta.
  • B. Al Jumum
    Al Jumum is a town and governorate in western Saudi Arabia, situated near the holy city of Mecca in the Makkah administrative region.
  • C. Shum
    Shum is a Chinese-origin surname borne by various notable individuals, including actors, politicians, and academics in the Chinese diaspora.
  • D. Shimsha
    Shimsha is a river in southern India that flows through Karnataka and is known for its waterfalls and contribution to the Kaveri river system.
  • E. Shalim
    Shalim is a deity from ancient Canaanite religion, commonly associated with dusk or the setting sun.
  • 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_69d886cc4170819093deddc7b8b4b6a7 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d5d5ed388190871aa738cac04b65 completed April 18, 2026, 7:04 p.m.
NED1 Entity disambiguation (via context triple) batch_6a011b53306081908972a0a5db474b6c completed May 10, 2026, 11:57 p.m.
NEDg Description generation batch_6a011cfb74b88190bbd5af862727790f completed May 11, 2026, 12:04 a.m.
NED2 Entity disambiguation (via description) batch_6a011dad838c8190a1ea560680c9ca57 completed May 11, 2026, 12:07 a.m.
Created at: April 10, 2026, 5:33 a.m.