Triple

T22296627
Position Surface form Disambiguated ID Type / Status
Subject Jarawan languages E551137 entity
Predicate hasMember P10 FINISHED
Object Mbat language
The Mbat language is a lesser-known Jarawan Bantu language spoken by a small community in Nigeria.
 E1529331 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: Mbat language | Statement: [Jarawan languages, hasMember, Mbat language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mbat language
Context triple: [Jarawan languages, hasMember, Mbat language]
  • A. Mbato language
    The Mbato language is a Niger-Congo language spoken in parts of West Africa, belonging to the Potou–Tano branch of the Kwa language family.
  • B. Mambae language
    The Mambae language is an Austronesian language spoken primarily in East Timor, notable for its role in local identity and traditional culture.
  • C. Babatana language
    The Babatana language is an Oceanic language spoken by indigenous communities on Choiseul Island in the Solomon Islands.
  • D. Maba language
    The Maba language is an Afro-Asiatic language spoken primarily by the Maba people in eastern Chad and neighboring regions.
  • E. Maba language
    The Maba language is an Austronesian language spoken in eastern Indonesia, particularly in the Halmahera region of North Maluku.
  • 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: Mbat language
Triple: [Jarawan languages, hasMember, Mbat language]
Generated description
The Mbat language is a lesser-known Jarawan Bantu language spoken by a small community in Nigeria.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mbat language
Target entity description: The Mbat language is a lesser-known Jarawan Bantu language spoken by a small community in Nigeria.
  • A. Mbato language
    The Mbato language is a Niger-Congo language spoken in parts of West Africa, belonging to the Potou–Tano branch of the Kwa language family.
  • B. Mambae language
    The Mambae language is an Austronesian language spoken primarily in East Timor, notable for its role in local identity and traditional culture.
  • C. Babatana language
    The Babatana language is an Oceanic language spoken by indigenous communities on Choiseul Island in the Solomon Islands.
  • D. Maba language
    The Maba language is an Afro-Asiatic language spoken primarily by the Maba people in eastern Chad and neighboring regions.
  • E. Maba language
    The Maba language is an Austronesian language spoken in eastern Indonesia, particularly in the Halmahera region of North Maluku.
  • 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_69e11e45fb848190a1b2ae21296e3a5f completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15720fba0819080f6c96f6df4f1e0 completed April 29, 2026, 12:56 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0acc9609788190a1e7306a47a3fb56 completed May 18, 2026, 8:23 a.m.
NEDg Description generation batch_6a0acd67a4c88190bf64d4ecad0491b9 completed May 18, 2026, 8:27 a.m.
NED2 Entity disambiguation (via description) batch_6a0acdcc02ac8190a35b572701410c80 completed May 18, 2026, 8:29 a.m.
Created at: April 16, 2026, 8:41 p.m.