Triple

T16615922
Position Surface form Disambiguated ID Type / Status
Subject Rejang script E403694 entity
Predicate historicalRegion P915 FINISHED
Object Curup
Curup is a town and historical region in Bengkulu Province on the Indonesian island of Sumatra, known as a cultural center for the Rejang people.
E1223843 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: Curup | Statement: [Rejang script, historicalRegion, Curup]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Curup
Context triple: [Rejang script, historicalRegion, Curup]
  • A. Carakan
    Carakan is the traditional Javanese writing system used for the Javanese language and related regional languages of Indonesia.
  • B. Pakurumo
    Pakurumo is a popular Afrobeat song by Nigerian artist Wizkid, known for its upbeat rhythm and dance-friendly vibe.
  • C. Papudo
    Papudo is a small coastal town and popular beach resort in central Chile known for its scenic bay and relaxed seaside atmosphere.
  • D. Contamana
    Contamana is a small Peruvian city in the Amazon rainforest, serving as a regional center in the Loreto region and accessible primarily by river and air.
  • E. Curumaní
    Curumaní is a municipality and important urban center in Colombia’s Caribbean-region Cesar Department, known for its agricultural economy and proximity to the Serranía del Perijá.
  • 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: Curup
Triple: [Rejang script, historicalRegion, Curup]
Generated description
Curup is a town and historical region in Bengkulu Province on the Indonesian island of Sumatra, known as a cultural center for the Rejang people.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Curup
Target entity description: Curup is a town and historical region in Bengkulu Province on the Indonesian island of Sumatra, known as a cultural center for the Rejang people.
  • A. Carakan
    Carakan is the traditional Javanese writing system used for the Javanese language and related regional languages of Indonesia.
  • B. Pakurumo
    Pakurumo is a popular Afrobeat song by Nigerian artist Wizkid, known for its upbeat rhythm and dance-friendly vibe.
  • C. Papudo
    Papudo is a small coastal town and popular beach resort in central Chile known for its scenic bay and relaxed seaside atmosphere.
  • D. Contamana
    Contamana is a small Peruvian city in the Amazon rainforest, serving as a regional center in the Loreto region and accessible primarily by river and air.
  • E. Curumaní
    Curumaní is a municipality and important urban center in Colombia’s Caribbean-region Cesar Department, known for its agricultural economy and proximity to the Serranía del Perijá.
  • 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_69d883897eb481909eaaa088ba9918d9 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e375494260819099b6988857c52dde completed April 18, 2026, 12:12 p.m.
NED1 Entity disambiguation (via context triple) batch_6a007daef18481908c3628a3466300ce completed May 10, 2026, 12:44 p.m.
NEDg Description generation batch_6a007e6507208190b3f32c05a2f647bd completed May 10, 2026, 12:47 p.m.
NED2 Entity disambiguation (via description) batch_6a007f2cefa081908734a907da33a72f completed May 10, 2026, 12:50 p.m.
Created at: April 10, 2026, 5:17 a.m.