Triple

T19302980
Position Surface form Disambiguated ID Type / Status
Subject Te Puke E482747 entity
Predicate hasNearbyAttraction P2064 FINISHED
Object Kiwi 360
Kiwi 360 is a tourism attraction in Te Puke, New Zealand, known for its giant kiwifruit structure and kiwifruit-themed tours and experiences.
E1368705 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: Kiwi 360 | Statement: [Te Puke, hasNearbyAttraction, Kiwi 360]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kiwi 360
Context triple: [Te Puke, hasNearbyAttraction, Kiwi 360]
  • A. kiwi pukupuku
    Kiwi pukupuku is the little spotted kiwi, a small, nocturnal, flightless bird native to New Zealand and one of the country’s rarest kiwi species.
  • B. KIWA
    KIWA is the ICAO airport code for Phoenix–Mesa Gateway Airport, a commercial and general aviation airport serving the Phoenix metropolitan area in Arizona, United States.
  • C. Kwikwi
    Kwikwi is a popular song by Tanzanian singer Zuchu, known for its catchy Bongo Flava style and wide acclaim in East Africa.
  • D. Kiwikapawa
    Kiwikapawa is the endonym used by the Kickapoo people to refer to themselves in their own language.
  • E. Kiwi
    Kiwi is the colloquial nickname for the New Zealand dollar, reflecting New Zealand’s national symbol and identity.
  • 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: Kiwi 360
Triple: [Te Puke, hasNearbyAttraction, Kiwi 360]
Generated description
Kiwi 360 is a tourism attraction in Te Puke, New Zealand, known for its giant kiwifruit structure and kiwifruit-themed tours and experiences.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kiwi 360
Target entity description: Kiwi 360 is a tourism attraction in Te Puke, New Zealand, known for its giant kiwifruit structure and kiwifruit-themed tours and experiences.
  • A. kiwi pukupuku
    Kiwi pukupuku is the little spotted kiwi, a small, nocturnal, flightless bird native to New Zealand and one of the country’s rarest kiwi species.
  • B. KIWA
    KIWA is the ICAO airport code for Phoenix–Mesa Gateway Airport, a commercial and general aviation airport serving the Phoenix metropolitan area in Arizona, United States.
  • C. Kwikwi
    Kwikwi is a popular song by Tanzanian singer Zuchu, known for its catchy Bongo Flava style and wide acclaim in East Africa.
  • D. Kiwikapawa
    Kiwikapawa is the endonym used by the Kickapoo people to refer to themselves in their own language.
  • E. Kiwi
    Kiwi is the colloquial nickname for the New Zealand dollar, reflecting New Zealand’s national symbol and identity.
  • 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_69d8e8d04d5c8190baa816986f2b1d1e completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e5fc8add788190aed98bcbad518808 completed April 20, 2026, 10:14 a.m.
NED1 Entity disambiguation (via context triple) batch_6a07145792608190857920fdaff261ef completed May 15, 2026, 12:40 p.m.
NEDg Description generation batch_6a0714fcd0248190a93297332599f74d completed May 15, 2026, 12:43 p.m.
NED2 Entity disambiguation (via description) batch_6a071542cf0c81908658008e0ee9fcbb completed May 15, 2026, 12:44 p.m.
Created at: April 10, 2026, 1:31 p.m.