Triple

T6243963
Position Surface form Disambiguated ID Type / Status
Subject Bungku–Tolaki languages E139669 entity
Predicate hasMember P10 FINISHED
Object Kulisusu language
The Kulisusu language is an Austronesian language spoken by the Kulisusu people of southeastern Sulawesi, Indonesia.
 E578970 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: Kulisusu language | Statement: [Bungku–Tolaki languages, hasMember, Kulisusu language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kulisusu language
Context triple: [Bungku–Tolaki languages, hasMember, Kulisusu language]
  • A. Kisukuma language
    Kisukuma is a major Bantu language spoken primarily by the Sukuma people in northwestern Tanzania.
  • B. Kalanguya language
    The Kalanguya language is an Austronesian language spoken by the Kalanguya people in the northern Luzon highlands of the Philippines.
  • C. Baliledu language
    The Baliledu language is an Austronesian language of the Bima–Sumba subgroup spoken by a local community in eastern Indonesia.
  • D. Sanglechi language
    The Sanglechi language is an Eastern Iranian language spoken by a small community in the Sanglech Valley region of Afghanistan and Tajikistan.
  • E. Kalinago language
    The Kalinago language is an extinct Cariban language once spoken by the indigenous Kalinago (Island Carib) people of the Lesser Antilles in the Caribbean.
  • 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: Kulisusu language
Triple: [Bungku–Tolaki languages, hasMember, Kulisusu language]
Generated description
The Kulisusu language is an Austronesian language spoken by the Kulisusu people of southeastern Sulawesi, Indonesia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kulisusu language
Target entity description: The Kulisusu language is an Austronesian language spoken by the Kulisusu people of southeastern Sulawesi, Indonesia.
  • A. Kisukuma language
    Kisukuma is a major Bantu language spoken primarily by the Sukuma people in northwestern Tanzania.
  • B. Kalanguya language
    The Kalanguya language is an Austronesian language spoken by the Kalanguya people in the northern Luzon highlands of the Philippines.
  • C. Baliledu language
    The Baliledu language is an Austronesian language of the Bima–Sumba subgroup spoken by a local community in eastern Indonesia.
  • D. Sanglechi language
    The Sanglechi language is an Eastern Iranian language spoken by a small community in the Sanglech Valley region of Afghanistan and Tajikistan.
  • E. Kalinago language
    The Kalinago language is an extinct Cariban language once spoken by the indigenous Kalinago (Island Carib) people of the Lesser Antilles in the Caribbean.
  • 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_69c008b1c5088190ae6de2555fc05ad8 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c0631b32308190a8211043d1caa6e6 completed March 22, 2026, 9:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69c20e12fa248190ad9daaf9563d38c6 completed March 24, 2026, 4:07 a.m.
NEDg Description generation batch_69c214aaef308190be1166c1389bf3d3 completed March 24, 2026, 4:35 a.m.
NED2 Entity disambiguation (via description) batch_69c21508dbec8190b9bb4806a83ecb13 completed March 24, 2026, 4:37 a.m.
Created at: March 22, 2026, 4:23 p.m.