Triple

T3730422
Position Surface form Disambiguated ID Type / Status
Subject Central Sulawesi E79046 entity
Predicate hasCity P316 FINISHED
Object Donggala
Donggala is a coastal town and regency in Indonesia known historically as a key port and administrative center in Central Sulawesi.
E390762 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: Donggala | Statement: [Central Sulawesi, hasCity, Donggala]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Donggala
Context triple: [Central Sulawesi, hasCity, Donggala]
  • A. Tidore
    Tidore is an island and historic sultanate in eastern Indonesia that was once a major center of the regional spice trade.
  • B. Ternate
    Ternate is a coastal municipality in the province of Cavite in the Philippines, known for its beaches and historical significance.
  • C. Ternate
    Ternate is a small volcanic island and city in eastern Indonesia that was historically a major center of the global spice trade, especially for cloves.
  • D. Kendari Bay
    Kendari Bay is a coastal inlet in Southeast Sulawesi, Indonesia, known for bordering the city of Kendari and serving as an important local hub for fishing, transport, and maritime activities.
  • E. Bawean
    Bawean is an Indonesian island in the Java Sea known for its volcanic landscape, unique endemic deer, and cultural blend of Javanese and Malay influences.
  • 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: Donggala
Triple: [Central Sulawesi, hasCity, Donggala]
Generated description
Donggala is a coastal town and regency in Indonesia known historically as a key port and administrative center in Central Sulawesi.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Donggala
Target entity description: Donggala is a coastal town and regency in Indonesia known historically as a key port and administrative center in Central Sulawesi.
  • A. Tidore
    Tidore is an island and historic sultanate in eastern Indonesia that was once a major center of the regional spice trade.
  • B. Ternate
    Ternate is a coastal municipality in the province of Cavite in the Philippines, known for its beaches and historical significance.
  • C. Ternate
    Ternate is a small volcanic island and city in eastern Indonesia that was historically a major center of the global spice trade, especially for cloves.
  • D. Kendari Bay
    Kendari Bay is a coastal inlet in Southeast Sulawesi, Indonesia, known for bordering the city of Kendari and serving as an important local hub for fishing, transport, and maritime activities.
  • E. Bawean
    Bawean is an Indonesian island in the Java Sea known for its volcanic landscape, unique endemic deer, and cultural blend of Javanese and Malay influences.
  • 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_69ad8b0e4650819090ad7cef094285e8 completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69adcb1bb5408190990ea4dfbdab5c68 completed March 8, 2026, 7:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4fb074a9881909afec640a5a208c6 completed March 14, 2026, 6:07 a.m.
NEDg Description generation batch_69b4fc9107fc81908805740b98c7ae3e completed March 14, 2026, 6:13 a.m.
NED2 Entity disambiguation (via description) batch_69b4fced2620819083ab1e75393ba2ba completed March 14, 2026, 6:15 a.m.
Created at: March 8, 2026, 3:34 p.m.