Triple

T13411509
Position Surface form Disambiguated ID Type / Status
Subject Mount Soputan E320097 entity
Predicate nearbySettlement P350 FINISHED
Object Ratahan
Ratahan is a town in North Sulawesi, Indonesia, known as an administrative and residential center situated near the active volcano Mount Soputan.
E1038838 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: Ratahan | Statement: [Mount Soputan, nearbySettlement, Ratahan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ratahan
Context triple: [Mount Soputan, nearbySettlement, Ratahan]
  • A. Sibolga
    Sibolga is a coastal city and port on the western coast of Sumatra, Indonesia, known as a gateway to nearby islands and marine tourism areas.
  • B. Bulukumba
    Bulukumba is a regency in South Sulawesi, Indonesia, known for its coastal landscapes, traditional boatbuilding, and Makassarese cultural heritage.
  • C. Tobelo
    Tobelo is a coastal town and important regional center in northern Halmahera, North Maluku, Indonesia.
  • D. Padang Bai
    Padang Bai is a small coastal village and port in eastern Bali, Indonesia, known as a gateway to the nearby islands and for its beaches and dive sites.
  • E. Melawi
    Melawi is a regency-level administrative area in the interior of West Kalimantan, Indonesia, known for its riverine landscapes and predominantly Dayak communities.
  • 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: Ratahan
Triple: [Mount Soputan, nearbySettlement, Ratahan]
Generated description
Ratahan is a town in North Sulawesi, Indonesia, known as an administrative and residential center situated near the active volcano Mount Soputan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ratahan
Target entity description: Ratahan is a town in North Sulawesi, Indonesia, known as an administrative and residential center situated near the active volcano Mount Soputan.
  • A. Sibolga
    Sibolga is a coastal city and port on the western coast of Sumatra, Indonesia, known as a gateway to nearby islands and marine tourism areas.
  • B. Bulukumba
    Bulukumba is a regency in South Sulawesi, Indonesia, known for its coastal landscapes, traditional boatbuilding, and Makassarese cultural heritage.
  • C. Tobelo
    Tobelo is a coastal town and important regional center in northern Halmahera, North Maluku, Indonesia.
  • D. Padang Bai
    Padang Bai is a small coastal village and port in eastern Bali, Indonesia, known as a gateway to the nearby islands and for its beaches and dive sites.
  • E. Melawi
    Melawi is a regency-level administrative area in the interior of West Kalimantan, Indonesia, known for its riverine landscapes and predominantly Dayak communities.
  • 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_69d806b943cc8190b6af624d385d7e12 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69dbaeb3facc819088c1af3b59237e7a completed April 12, 2026, 2:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69f7307e9b5881908eb2cd9e4fa7c5f2 completed May 3, 2026, 11:24 a.m.
NEDg Description generation batch_69f73195e4d88190ad356d0e3e18d34f completed May 3, 2026, 11:29 a.m.
NED2 Entity disambiguation (via description) batch_69f73220ffc08190bfb1b89757efd606 completed May 3, 2026, 11:31 a.m.
Created at: April 9, 2026, 9:35 p.m.