Triple

T19006441
Position Surface form Disambiguated ID Type / Status
Subject Sool region E465096 entity
Predicate hasTown P847 FINISHED
Object Hudun
Hudun is a town in the Sool region of northern Somalia, serving as a local administrative and commercial center for surrounding rural communities.
 E1353884 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: Hudun | Statement: [Sool region, hasTown, Hudun]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Hudun
Context triple: [Sool region, hasTown, Hudun]
  • A. Hamtunam
    Hamtunam is an alternative historical or linguistic spelling variant of the place name Hamtun.
  • B. Dromahane
    Dromahane is a village in County Cork, Ireland, situated near the town of Mallow in the north of the county.
  • C. Gharaunda
    Gharaunda is a town in the Indian state of Haryana known for its agricultural market and proximity to the historic city of Karnal.
  • D. Dunum
    Dunum is a small locality in the Wittmund district of Lower Saxony, Germany, known as a rural community within the East Frisian region.
  • E. Khusf
    Khusf is a small city in eastern Iran that serves as one of the urban centers of South Khorasan Province.
  • 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: Hudun
Triple: [Sool region, hasTown, Hudun]
Generated description
Hudun is a town in the Sool region of northern Somalia, serving as a local administrative and commercial center for surrounding rural communities.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Hudun
Target entity description: Hudun is a town in the Sool region of northern Somalia, serving as a local administrative and commercial center for surrounding rural communities.
  • A. Hamtunam
    Hamtunam is an alternative historical or linguistic spelling variant of the place name Hamtun.
  • B. Dromahane
    Dromahane is a village in County Cork, Ireland, situated near the town of Mallow in the north of the county.
  • C. Gharaunda
    Gharaunda is a town in the Indian state of Haryana known for its agricultural market and proximity to the historic city of Karnal.
  • D. Dunum
    Dunum is a small locality in the Wittmund district of Lower Saxony, Germany, known as a rural community within the East Frisian region.
  • E. Khusf
    Khusf is a small city in eastern Iran that serves as one of the urban centers of South Khorasan Province.
  • 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_69d8dd01a56c81909694a128c66b21d7 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d6a561848190bd957f248471c191 completed April 20, 2026, 7:32 a.m.
NED1 Entity disambiguation (via context triple) batch_6a05b463d4a08190b15403ea0ad23682 completed May 14, 2026, 11:39 a.m.
NEDg Description generation batch_6a05b5dfac0c8190b67921280d5ab1fe completed May 14, 2026, 11:45 a.m.
NED2 Entity disambiguation (via description) batch_6a05b68aba3081908ca21d732e45f454 completed May 14, 2026, 11:48 a.m.
Created at: April 10, 2026, 12:01 p.m.