Triple

T23174989
Position Surface form Disambiguated ID Type / Status
Subject Kulisusu language E578970 entity
Predicate hasDialects P4251 FINISHED
Object Taloki
Taloki is a regional dialect of the Kulisusu language spoken by communities in parts of Southeast Sulawesi, Indonesia.
E1578235 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: Taloki | Statement: [Kulisusu language, hasDialects, Taloki]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Taloki
Context triple: [Kulisusu language, hasDialects, Taloki]
  • A. Talho
    Talho is a settlement located within the municipality of Ribeira Brava in Cape Verde.
  • B. Lohra
    Lohra is a small municipality in the Marburg-Biedenkopf district of the German state of Hesse.
  • C. Talasani
    Talasani is a small commune in the Haute-Corse department on the island of Corsica in France.
  • D. Sutala
    Sutala is a subterranean realm in Hindu cosmology, known as one of the lower worlds inhabited by the generous demon king Bali and protected by the god Vishnu.
  • E. Talauma
    Talauma is a genus of flowering plants in the magnolia family, known for its large, often fragrant blossoms and tropical to subtropical distribution.
  • 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: Taloki
Triple: [Kulisusu language, hasDialects, Taloki]
Generated description
Taloki is a regional dialect of the Kulisusu language spoken by communities in parts of Southeast Sulawesi, Indonesia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Taloki
Target entity description: Taloki is a regional dialect of the Kulisusu language spoken by communities in parts of Southeast Sulawesi, Indonesia.
  • A. Talho
    Talho is a settlement located within the municipality of Ribeira Brava in Cape Verde.
  • B. Lohra
    Lohra is a small municipality in the Marburg-Biedenkopf district of the German state of Hesse.
  • C. Talasani
    Talasani is a small commune in the Haute-Corse department on the island of Corsica in France.
  • D. Sutala
    Sutala is a subterranean realm in Hindu cosmology, known as one of the lower worlds inhabited by the generous demon king Bali and protected by the god Vishnu.
  • E. Talauma
    Talauma is a genus of flowering plants in the magnolia family, known for its large, often fragrant blossoms and tropical to subtropical distribution.
  • 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_69e245fd2a388190b814c0dfa15f7148 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f18f69cb1881909e0f47d3b32e2cb1 completed April 29, 2026, 4:56 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c3f4652c48190aa90bf5ed5f5fd0f completed May 19, 2026, 10:45 a.m.
NEDg Description generation batch_6a0c4161607881909644f9891472766b completed May 19, 2026, 10:54 a.m.
NED2 Entity disambiguation (via description) batch_6a0c41d690a88190b794bacd1d23a823 completed May 19, 2026, 10:56 a.m.
Created at: April 17, 2026, 4:04 p.m.