Triple

T18503627
Position Surface form Disambiguated ID Type / Status
Subject SPK E452142 entity
Predicate originalName P65 FINISHED
Object SePuKu
SePuKu, also known as SPK, is likely a creative or stage name used by an individual or group, such as a musician, artist, or online persona.
 E1328256 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: SePuKu | Statement: [SPK, originalName, SePuKu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SePuKu
Context triple: [SPK, originalName, SePuKu]
  • A. Tuktukan
    Tuktukan is a barangay (village-level administrative division) in the city of Taguig in Metro Manila, Philippines.
  • B. Sepetiba
    Sepetiba is a coastal neighborhood in Rio de Janeiro known for its bay, fishing activities, and industrial port area.
  • C. Panjalu
    Panjalu was a historical Javanese kingdom that emerged as a major political power in eastern Java following the decline of Kahuripan.
  • D. Pangyo
    Pangyo is a planned high-tech new town in Seongnam, South Korea, known as a major IT and startup hub often dubbed the "Korean Silicon Valley."
  • E. Kulisusu
    Kulisusu is a town and administrative center located in the province of Southeast Sulawesi, Indonesia.
  • 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: SePuKu
Triple: [SPK, originalName, SePuKu]
Generated description
SePuKu, also known as SPK, is likely a creative or stage name used by an individual or group, such as a musician, artist, or online persona.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SePuKu
Target entity description: SePuKu, also known as SPK, is likely a creative or stage name used by an individual or group, such as a musician, artist, or online persona.
  • A. Tuktukan
    Tuktukan is a barangay (village-level administrative division) in the city of Taguig in Metro Manila, Philippines.
  • B. Sepetiba
    Sepetiba is a coastal neighborhood in Rio de Janeiro known for its bay, fishing activities, and industrial port area.
  • C. Panjalu
    Panjalu was a historical Javanese kingdom that emerged as a major political power in eastern Java following the decline of Kahuripan.
  • D. Pangyo
    Pangyo is a planned high-tech new town in Seongnam, South Korea, known as a major IT and startup hub often dubbed the "Korean Silicon Valley."
  • E. Kulisusu
    Kulisusu is a town and administrative center located in the province of Southeast Sulawesi, Indonesia.
  • 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_69d8d386df84819092355ebb260d848e completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e532c6384c819091f061c8538f6ca1 completed April 19, 2026, 7:53 p.m.
NED1 Entity disambiguation (via context triple) batch_6a047143903c8190979d96780689a068 completed May 13, 2026, 12:40 p.m.
NEDg Description generation batch_6a0486327b6c8190ac089fcc834582ff completed May 13, 2026, 2:09 p.m.
NED2 Entity disambiguation (via description) batch_6a0486d31e2c81908ca95db7baec64a0 completed May 13, 2026, 2:12 p.m.
Created at: April 10, 2026, 11:36 a.m.