Triple

T8798143
Position Surface form Disambiguated ID Type / Status
Subject Kingdom of Sunda E209338 entity
Predicate titleOfRuler P10605 FINISHED
Object Prabu
Prabu is a royal title historically used for kings or rulers in the Sundanese Kingdom of West Java, Indonesia.
E759786 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: Prabu | Statement: [Kingdom of Sunda, titleOfRuler, Prabu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Prabu
Context triple: [Kingdom of Sunda, titleOfRuler, Prabu]
  • A. Prabu Padjadjaran
    Prabu Padjadjaran is a legendary Sundanese king associated with the historical Padjadjaran kingdom in West Java, Indonesia.
  • B. Samaratungga
    Samaratungga was a 9th-century Javanese king of the Sailendra dynasty best known for commissioning the construction of the monumental Borobudur Buddhist temple in Central Java.
  • C. Tribhuwana
    Tribhuwana is the regnal name of a 14th-century Javanese queen of the Majapahit Empire, formally known as Tribhuwana Wijayatunggadewi.
  • D. Jayabaya
    Jayabaya was a legendary 12th-century king of the Kediri Kingdom in Java, renowned in Indonesian history and folklore for his just rule and prophetic visions.
  • E. Indera Putera
    Indera Putera is a legendary prince-hero from Malay literary tradition, known for his adventures and appearances in classical hikayat (epic tales).
  • 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: Prabu
Triple: [Kingdom of Sunda, titleOfRuler, Prabu]
Generated description
Prabu is a royal title historically used for kings or rulers in the Sundanese Kingdom of West Java, Indonesia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Prabu
Target entity description: Prabu is a royal title historically used for kings or rulers in the Sundanese Kingdom of West Java, Indonesia.
  • A. Prabu Padjadjaran
    Prabu Padjadjaran is a legendary Sundanese king associated with the historical Padjadjaran kingdom in West Java, Indonesia.
  • B. Samaratungga
    Samaratungga was a 9th-century Javanese king of the Sailendra dynasty best known for commissioning the construction of the monumental Borobudur Buddhist temple in Central Java.
  • C. Tribhuwana
    Tribhuwana is the regnal name of a 14th-century Javanese queen of the Majapahit Empire, formally known as Tribhuwana Wijayatunggadewi.
  • D. Jayabaya
    Jayabaya was a legendary 12th-century king of the Kediri Kingdom in Java, renowned in Indonesian history and folklore for his just rule and prophetic visions.
  • E. Indera Putera
    Indera Putera is a legendary prince-hero from Malay literary tradition, known for his adventures and appearances in classical hikayat (epic tales).
  • 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_69ca836240888190a62b262e56a69d2f completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc5fa50dd081908fa5e4ffa70342e2 completed March 31, 2026, 11:58 p.m.
NED1 Entity disambiguation (via context triple) batch_69cf6f658f248190957eba821b07cc4f completed April 3, 2026, 7:42 a.m.
NEDg Description generation batch_69cf713a184c8190b1fa788fd3ba8304 completed April 3, 2026, 7:50 a.m.
NED2 Entity disambiguation (via description) batch_69cf71d3517c819088c930ed468c4e8e completed April 3, 2026, 7:52 a.m.
Created at: March 30, 2026, 6:44 p.m.