Triple

T6688527
Position Surface form Disambiguated ID Type / Status
Subject Mandar language E152161 entity
Predicate hasDialect P4251 FINISHED
Object Sendana dialect
The Sendana dialect is a regional variety of the Mandar language spoken by communities in the Sendana area of West Sulawesi, Indonesia.
 E610786 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: Sendana dialect | Statement: [Mandar language, hasDialect, Sendana dialect]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sendana dialect
Context triple: [Mandar language, hasDialect, Sendana dialect]
  • A. Satawan dialect
    The Satawan dialect is a regional variety of the Mortlockese language spoken primarily on Satawan Atoll in the Federated States of Micronesia.
  • B. Ayt Sokhman dialect
    The Ayt Sokhman dialect is a regional variety of Central Atlas Tamazight spoken by the Ayt Sokhman Amazigh community in Morocco.
  • C. Sari dialect
    The Sari dialect is a regional variety of the Mazanderani language spoken in and around the city of Sari in northern Iran.
  • D. Sadz dialect
    The Sadz dialect is a regional variety of the Abkhaz language traditionally spoken by the Sadz subgroup of Abkhazians along the Black Sea coast.
  • E. Takbanuaz dialect
    The Takbanuaz dialect is a regional variety of the Bunun language spoken by an indigenous Bunun subgroup in Taiwan.
  • 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: Sendana dialect
Triple: [Mandar language, hasDialect, Sendana dialect]
Generated description
The Sendana dialect is a regional variety of the Mandar language spoken by communities in the Sendana area of West Sulawesi, Indonesia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sendana dialect
Target entity description: The Sendana dialect is a regional variety of the Mandar language spoken by communities in the Sendana area of West Sulawesi, Indonesia.
  • A. Satawan dialect
    The Satawan dialect is a regional variety of the Mortlockese language spoken primarily on Satawan Atoll in the Federated States of Micronesia.
  • B. Ayt Sokhman dialect
    The Ayt Sokhman dialect is a regional variety of Central Atlas Tamazight spoken by the Ayt Sokhman Amazigh community in Morocco.
  • C. Sari dialect
    The Sari dialect is a regional variety of the Mazanderani language spoken in and around the city of Sari in northern Iran.
  • D. Sadz dialect
    The Sadz dialect is a regional variety of the Abkhaz language traditionally spoken by the Sadz subgroup of Abkhazians along the Black Sea coast.
  • E. Takbanuaz dialect
    The Takbanuaz dialect is a regional variety of the Bunun language spoken by an indigenous Bunun subgroup in Taiwan.
  • 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_69c687f9977c819097e7f5ada4fe522e completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6b14feb28819097bc157df8a2f96e completed March 27, 2026, 4:33 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6f7b31fa0819089c4debbbbce9d22 completed March 27, 2026, 9:33 p.m.
NEDg Description generation batch_69c6f8d27d388190816cfeefbe1519d8 completed March 27, 2026, 9:38 p.m.
NED2 Entity disambiguation (via description) batch_69c6f9729d7881908f3c396690ffcae8 completed March 27, 2026, 9:41 p.m.
Created at: March 27, 2026, 2:04 p.m.