Triple

T10837246
Position Surface form Disambiguated ID Type / Status
Subject Berta E255792 entity
Predicate hasDialect P4251 FINISHED
Object Undu
Undu is a regional dialect of the Berta language spoken by communities in parts of Ethiopia and Sudan.
 E889287 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: Undu | Statement: [Berta, hasDialect, Undu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Undu
Context triple: [Berta, hasDialect, Undu]
  • A. Ngundu
    Ngundu is a small settlement in southern Zimbabwe that serves as a roadside stop and trading center along major routes between Harare and Beitbridge.
  • B. Undun
    Undun is a concept album by hip hop band The Roots that narrates the rise and fall of a fictional young man through introspective, jazz-influenced production and storytelling.
  • C. Umunede
    Umunede is a prominent town in Delta State, Nigeria, known as one of the key communities of the Anioma (Igbo-speaking) people.
  • D. Dondo
    Dondo is an Austronesian language spoken in Central Sulawesi, Indonesia, belonging to the Tomini–Tolitoli subgroup.
  • E. Dunda
    Dunda is a village located in the Uttarkashi district of the Indian state of Uttarakhand, in the Himalayan region of northern India.
  • 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: Undu
Triple: [Berta, hasDialect, Undu]
Generated description
Undu is a regional dialect of the Berta language spoken by communities in parts of Ethiopia and Sudan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Undu
Target entity description: Undu is a regional dialect of the Berta language spoken by communities in parts of Ethiopia and Sudan.
  • A. Ngundu
    Ngundu is a small settlement in southern Zimbabwe that serves as a roadside stop and trading center along major routes between Harare and Beitbridge.
  • B. Undun
    Undun is a concept album by hip hop band The Roots that narrates the rise and fall of a fictional young man through introspective, jazz-influenced production and storytelling.
  • C. Umunede
    Umunede is a prominent town in Delta State, Nigeria, known as one of the key communities of the Anioma (Igbo-speaking) people.
  • D. Dondo
    Dondo is an Austronesian language spoken in Central Sulawesi, Indonesia, belonging to the Tomini–Tolitoli subgroup.
  • E. Dunda
    Dunda is a village located in the Uttarkashi district of the Indian state of Uttarakhand, in the Himalayan region of northern India.
  • 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_69d6aa81a5d08190aa86689061d1ddd2 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d746ff70148190b844ab92d796af6c completed April 9, 2026, 6:28 a.m.
NED1 Entity disambiguation (via context triple) batch_69deb12aae648190aa7c93cee60ae3ea completed April 14, 2026, 9:27 p.m.
NEDg Description generation batch_69dec2534728819095b3693120772da9 completed April 14, 2026, 10:40 p.m.
NED2 Entity disambiguation (via description) batch_69dec79b1b548190a74312284f98551c completed April 14, 2026, 11:02 p.m.
Created at: April 8, 2026, 9:19 p.m.