Triple

T16131788
Position Surface form Disambiguated ID Type / Status
Subject Kapiti Coast E391415 entity
Predicate hasSuburb P747 FINISHED
Object Peka Peka
Peka Peka is a small coastal settlement on New Zealand’s Kāpiti Coast, known for its quiet beachside character and natural surroundings.
E1195293 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: Peka Peka | Statement: [Kapiti Coast, hasSuburb, Peka Peka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Peka Peka
Context triple: [Kapiti Coast, hasSuburb, Peka Peka]
  • A. Pukanec
    Pukanec is a historic village and former mining town in central Slovakia known for its past silver and gold extraction.
  • B. Pakurumo
    Pakurumo is a popular Afrobeat song by Nigerian artist Wizkid, known for its upbeat rhythm and dance-friendly vibe.
  • C. Ko Poda
    Ko Poda is a small, scenic island in Thailand’s Andaman Sea, known for its white-sand beaches, clear turquoise waters, and limestone cliffs, and is a popular day-trip destination from Krabi.
  • D. Pangkajene
    Pangkajene is a town in South Sulawesi, Indonesia, serving as the administrative and economic center of the Pangkajene and Islands Regency.
  • E. Tongaat
    Tongaat is a town in KwaZulu-Natal, South Africa, known for its significant Indian community and sugar industry.
  • 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: Peka Peka
Triple: [Kapiti Coast, hasSuburb, Peka Peka]
Generated description
Peka Peka is a small coastal settlement on New Zealand’s Kāpiti Coast, known for its quiet beachside character and natural surroundings.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Peka Peka
Target entity description: Peka Peka is a small coastal settlement on New Zealand’s Kāpiti Coast, known for its quiet beachside character and natural surroundings.
  • A. Pukanec
    Pukanec is a historic village and former mining town in central Slovakia known for its past silver and gold extraction.
  • B. Pakurumo
    Pakurumo is a popular Afrobeat song by Nigerian artist Wizkid, known for its upbeat rhythm and dance-friendly vibe.
  • C. Ko Poda
    Ko Poda is a small, scenic island in Thailand’s Andaman Sea, known for its white-sand beaches, clear turquoise waters, and limestone cliffs, and is a popular day-trip destination from Krabi.
  • D. Pangkajene
    Pangkajene is a town in South Sulawesi, Indonesia, serving as the administrative and economic center of the Pangkajene and Islands Regency.
  • E. Tongaat
    Tongaat is a town in KwaZulu-Natal, South Africa, known for its significant Indian community and sugar industry.
  • 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_69d87f1bb0988190b490d273dbf3fd03 completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e21a02172c8190978f7951ccd80928 completed April 17, 2026, 11:31 a.m.
NED1 Entity disambiguation (via context triple) batch_69fff2b1b7248190a1bba4a87db8318b completed May 10, 2026, 2:51 a.m.
NEDg Description generation batch_69fff3478bfc8190bbcc0afbf6dbb089 completed May 10, 2026, 2:53 a.m.
NED2 Entity disambiguation (via description) batch_69fff3d29f50819093a9355d016f48dd completed May 10, 2026, 2:56 a.m.
Created at: April 10, 2026, 5:01 a.m.