Triple

T20754056
Position Surface form Disambiguated ID Type / Status
Subject Semarang Regency E510803 entity
Predicate capital P234 FINISHED
Object Ungaran
Ungaran is a town in Central Java, Indonesia, known as an administrative and economic center within the Semarang metropolitan area.
E1448966 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: Ungaran | Statement: [Semarang Regency, capital, Ungaran]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ungaran
Context triple: [Semarang Regency, capital, Ungaran]
  • A. Salatiga
    Salatiga is a small city in Central Java, Indonesia, known for its cool climate, educational institutions, and location between Mount Merbabu and Mount Telomoyo.
  • B. Kotamobagu
    Kotamobagu is a city in North Sulawesi, Indonesia, known as an administrative and economic center in the Bolaang Mongondow region.
  • C. Purworejo
    Purworejo is a regency in Central Java, Indonesia, known for its agricultural landscape and proximity to the southern coast of Java.
  • D. Blora
    Blora is a regency-level town in Indonesia known for its teak forests and cultural heritage, located in the eastern part of Central Java.
  • E. Blitar
    Blitar is a city in East Java, Indonesia, best known as the hometown and final resting place of the country’s first president, Sukarno.
  • 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: Ungaran
Triple: [Semarang Regency, capital, Ungaran]
Generated description
Ungaran is a town in Central Java, Indonesia, known as an administrative and economic center within the Semarang metropolitan area.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ungaran
Target entity description: Ungaran is a town in Central Java, Indonesia, known as an administrative and economic center within the Semarang metropolitan area.
  • A. Salatiga
    Salatiga is a small city in Central Java, Indonesia, known for its cool climate, educational institutions, and location between Mount Merbabu and Mount Telomoyo.
  • B. Kotamobagu
    Kotamobagu is a city in North Sulawesi, Indonesia, known as an administrative and economic center in the Bolaang Mongondow region.
  • C. Purworejo
    Purworejo is a regency in Central Java, Indonesia, known for its agricultural landscape and proximity to the southern coast of Java.
  • D. Blora
    Blora is a regency-level town in Indonesia known for its teak forests and cultural heritage, located in the eastern part of Central Java.
  • E. Blitar
    Blitar is a city in East Java, Indonesia, best known as the hometown and final resting place of the country’s first president, Sukarno.
  • 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_69e0b4c909ec8190b05987f1639513f6 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c22d0ebc8190b17077326f540f98 completed April 21, 2026, 12:17 a.m.
NED1 Entity disambiguation (via context triple) batch_6a08e8489c188190a79c573f8470445c completed May 16, 2026, 9:57 p.m.
NEDg Description generation batch_6a08e9a399f88190aab9e52277113271 completed May 16, 2026, 10:03 p.m.
NED2 Entity disambiguation (via description) batch_6a08ea0f4b60819093de46bd7543df38 completed May 16, 2026, 10:05 p.m.
Created at: April 16, 2026, 12:34 p.m.