Triple

T21473483
Position Surface form Disambiguated ID Type / Status
Subject Choiseul languages E529791 entity
Predicate hasMember P10 FINISHED
Object Kusaghe language
The Kusaghe language is an Oceanic language spoken by communities on Choiseul Island in the Solomon Islands.
 E1486391 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: Kusaghe language | Statement: [Choiseul languages, hasMember, Kusaghe language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kusaghe language
Context triple: [Choiseul languages, hasMember, Kusaghe language]
  • A. Kumbewaha language
    The Kumbewaha language is an Austronesian language spoken in Sulawesi, Indonesia, belonging to the Wotu–Wolio subgroup.
  • B. Kwegu language
    The Kwegu language is a Surmic language spoken by the small Kwegu ethnic group living along the Omo River in southwestern Ethiopia.
  • C. Kulisusu language
    The Kulisusu language is an Austronesian language spoken by the Kulisusu people of southeastern Sulawesi, Indonesia.
  • D. Makhuwa-Enahara language
    The Makhuwa-Enahara language is a Bantu language spoken primarily in northern Mozambique as one of the varieties of the broader Makhuwa language cluster.
  • E. Teke-Kukuya language
    The Teke-Kukuya language is a Bantu language spoken by the Teke-Kukuya people in the Republic of the Congo and neighboring regions of Central Africa.
  • 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: Kusaghe language
Triple: [Choiseul languages, hasMember, Kusaghe language]
Generated description
The Kusaghe language is an Oceanic language spoken by communities on Choiseul Island in the Solomon Islands.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kusaghe language
Target entity description: The Kusaghe language is an Oceanic language spoken by communities on Choiseul Island in the Solomon Islands.
  • A. Kumbewaha language
    The Kumbewaha language is an Austronesian language spoken in Sulawesi, Indonesia, belonging to the Wotu–Wolio subgroup.
  • B. Kwegu language
    The Kwegu language is a Surmic language spoken by the small Kwegu ethnic group living along the Omo River in southwestern Ethiopia.
  • C. Kulisusu language
    The Kulisusu language is an Austronesian language spoken by the Kulisusu people of southeastern Sulawesi, Indonesia.
  • D. Makhuwa-Enahara language
    The Makhuwa-Enahara language is a Bantu language spoken primarily in northern Mozambique as one of the varieties of the broader Makhuwa language cluster.
  • E. Teke-Kukuya language
    The Teke-Kukuya language is a Bantu language spoken by the Teke-Kukuya people in the Republic of the Congo and neighboring regions of Central Africa.
  • 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_69e0c459acb481909bb6ee452a0045c7 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69e9ea156dac819087c4594d022d3df6 completed April 23, 2026, 9:44 a.m.
NED1 Entity disambiguation (via context triple) batch_6a09cff96dbc8190adae0f91749530e4 completed May 17, 2026, 2:26 p.m.
NEDg Description generation batch_6a09d08ffa3c8190b5ab7e4cbf78719f completed May 17, 2026, 2:28 p.m.
NED2 Entity disambiguation (via description) batch_6a09d18c77e481908a353d443d79b7ca completed May 17, 2026, 2:32 p.m.
Created at: April 16, 2026, 6:19 p.m.