Triple

T20856828
Position Surface form Disambiguated ID Type / Status
Subject Karo people E513501 entity
Predicate clan P1915 FINISHED
Object Sembiring
Sembiring is one of the principal patrilineal clans of the Karo ethnic group of North Sumatra, Indonesia, with its own distinct lineages and cultural traditions.
E1454416 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: Sembiring | Statement: [Karo people, clan, Sembiring]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sembiring
Context triple: [Karo people, clan, Sembiring]
  • A. Tampaksiring
    Tampaksiring is a town in central Bali, Indonesia, known for its sacred Tirta Empul water temple and nearby presidential palace.
  • B. Sidenreng Rappang
    Sidenreng Rappang is a regency in South Sulawesi, Indonesia, known for its agricultural activities and Bugis cultural heritage.
  • C. Tumpang
    Tumpang is a subdistrict in Malang Regency, East Java, Indonesia, known for its proximity to historical temples and as a gateway to the Bromo-Tengger-Semeru area.
  • D. Kepahiang
    Kepahiang is a region in Bengkulu, Sumatra, Indonesia, historically associated with the Rejang people and their traditional Rejang script.
  • E. Simpang Rimba
    Simpang Rimba is a village-level settlement located within South Bangka Regency on Bangka Island in Indonesia’s Bangka Belitung Islands province.
  • 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: Sembiring
Triple: [Karo people, clan, Sembiring]
Generated description
Sembiring is one of the principal patrilineal clans of the Karo ethnic group of North Sumatra, Indonesia, with its own distinct lineages and cultural traditions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sembiring
Target entity description: Sembiring is one of the principal patrilineal clans of the Karo ethnic group of North Sumatra, Indonesia, with its own distinct lineages and cultural traditions.
  • A. Tampaksiring
    Tampaksiring is a town in central Bali, Indonesia, known for its sacred Tirta Empul water temple and nearby presidential palace.
  • B. Sidenreng Rappang
    Sidenreng Rappang is a regency in South Sulawesi, Indonesia, known for its agricultural activities and Bugis cultural heritage.
  • C. Tumpang
    Tumpang is a subdistrict in Malang Regency, East Java, Indonesia, known for its proximity to historical temples and as a gateway to the Bromo-Tengger-Semeru area.
  • D. Sesetan
    Sesetan is an urban village and administrative area within Denpasar, the capital city of Bali, Indonesia.
  • E. Kepahiang
    Kepahiang is a region in Bengkulu, Sumatra, Indonesia, historically associated with the Rejang people and their traditional Rejang script.
  • 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_69e0b4f5b01081909452f654d2fc3f50 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c3a93ea881909b9f80a9bd0605b6 completed April 21, 2026, 12:24 a.m.
NED1 Entity disambiguation (via context triple) batch_6a090b0b4e7081908cd82bdf8f8544af completed May 17, 2026, 12:25 a.m.
NEDg Description generation batch_6a090d4ae67c8190ad32f284088e1e39 completed May 17, 2026, 12:35 a.m.
NED2 Entity disambiguation (via description) batch_6a090e08c9348190a8b707e23da926db completed May 17, 2026, 12:38 a.m.
Created at: April 16, 2026, 12:44 p.m.