Triple

T10489757
Position Surface form Disambiguated ID Type / Status
Subject Koman E247383 entity
Predicate hasMemberLanguage P7390 FINISHED
Object Gule
Gule is a lesser-known language belonging to the Koman group of languages spoken in the border regions of Ethiopia and Sudan.
E867112 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: Gule | Statement: [Koman, hasMemberLanguage, Gule]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gule
Context triple: [Koman, hasMemberLanguage, Gule]
  • A. Blau
    The Blau is a small river in the German state of Baden-Württemberg that flows through the city of Blaustein before joining the Danube.
  • B. Rufaa
    Rufaa is a town in Sudan located in Al Jazirah state, known primarily as an agricultural and trading center along the Blue Nile.
  • C. Borouge
    Borouge is a leading petrochemicals company based in the United Arab Emirates, specializing in the production of polyolefins for packaging, infrastructure, and industrial applications.
  • D. Loha
    Loha is a 1987 Indian Hindi-language action film featuring Persis Khambatta in a prominent role.
  • E. Beigem
    Beigem is a village in the Flemish Brabant province of Belgium, known as a sub-municipality of Grimbergen.
  • 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: Gule
Triple: [Koman, hasMemberLanguage, Gule]
Generated description
Gule is a lesser-known language belonging to the Koman group of languages spoken in the border regions of Ethiopia and Sudan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Gule
Target entity description: Gule is a lesser-known language belonging to the Koman group of languages spoken in the border regions of Ethiopia and Sudan.
  • A. Blau
    The Blau is a small river in the German state of Baden-Württemberg that flows through the city of Blaustein before joining the Danube.
  • B. Rufaa
    Rufaa is a town in Sudan located in Al Jazirah state, known primarily as an agricultural and trading center along the Blue Nile.
  • C. Borouge
    Borouge is a leading petrochemicals company based in the United Arab Emirates, specializing in the production of polyolefins for packaging, infrastructure, and industrial applications.
  • D. Loha
    Loha is a 1987 Indian Hindi-language action film featuring Persis Khambatta in a prominent role.
  • E. Beigem
    Beigem is a village in the Flemish Brabant province of Belgium, known as a sub-municipality of Grimbergen.
  • 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_69d381c309b88190af78aa681cf6a4c2 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d5097ca5c081908b47a08ca7885650 completed April 7, 2026, 1:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69d8dc9792308190b09d6aaed63dd418 completed April 10, 2026, 11:18 a.m.
NEDg Description generation batch_69d8e8c81bdc8190b6b6dfe00025b514 completed April 10, 2026, 12:10 p.m.
NED2 Entity disambiguation (via description) batch_69d901e1ecf88190acd24a0e20462cb9 completed April 10, 2026, 1:57 p.m.
Created at: April 6, 2026, 12:23 p.m.