Triple

T2076929
Position Surface form Disambiguated ID Type / Status
Subject Cook Islands E44944 entity
Predicate hasIsland P970 FINISHED
Object Pukapuka
Pukapuka is a remote, culturally distinctive coral atoll in the northern Cook Islands known for its traditional Polynesian lifestyle and unique language dialect.
 E230623 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: Pukapuka | Statement: [Cook Islands, hasIsland, Pukapuka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Pukapuka
Context triple: [Cook Islands, hasIsland, Pukapuka]
  • A. Pan Books
    Pan Books is a British publishing imprint known for producing popular fiction and classic titles, including major science fiction works.
  • B. Kapa o Pango
    Kapa o Pango is a modern, specially composed haka performed by New Zealand’s All Blacks rugby team to express their identity, strength, and connection to Māori culture.
  • C. The Peg
    The Peg is a colloquial nickname for Winnipeg, the capital and largest city of the Canadian province of Manitoba.
  • D. Makatib
    Makatib is a collection of letters by the Persian Sufi poet Rumi, offering spiritual guidance, personal counsel, and insights into his mystical thought and relationships.
  • E. The Paper
    The Paper is a 1994 American comedy-drama film directed by Ron Howard that follows the hectic, deadline-driven day at a New York City tabloid newspaper.
  • 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: Pukapuka
Triple: [Cook Islands, hasIsland, Pukapuka]
Generated description
Pukapuka is a remote, culturally distinctive coral atoll in the northern Cook Islands known for its traditional Polynesian lifestyle and unique language dialect.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Pukapuka
Target entity description: Pukapuka is a remote, culturally distinctive coral atoll in the northern Cook Islands known for its traditional Polynesian lifestyle and unique language dialect.
  • A. Pan Books
    Pan Books is a British publishing imprint known for producing popular fiction and classic titles, including major science fiction works.
  • B. Kapa o Pango
    Kapa o Pango is a modern, specially composed haka performed by New Zealand’s All Blacks rugby team to express their identity, strength, and connection to Māori culture.
  • C. The Peg
    The Peg is a colloquial nickname for Winnipeg, the capital and largest city of the Canadian province of Manitoba.
  • D. Makatib
    Makatib is a collection of letters by the Persian Sufi poet Rumi, offering spiritual guidance, personal counsel, and insights into his mystical thought and relationships.
  • E. The Paper
    The Paper is a 1994 American comedy-drama film directed by Ron Howard that follows the hectic, deadline-driven day at a New York City tabloid newspaper.
  • 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_69a88916c2b48190a5ca2e9b12cad3ed completed March 4, 2026, 7:33 p.m.
NER Named-entity recognition batch_69abba2fa9c48190958826d5226544df completed March 7, 2026, 5:39 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae2734a0688190a43c9687af48d06d completed March 9, 2026, 1:49 a.m.
NEDg Description generation batch_69ae28155ec8819097741dcfd3d81110 completed March 9, 2026, 1:53 a.m.
NED2 Entity disambiguation (via description) batch_69ae2889503c8190bc72e786c656edf3 completed March 9, 2026, 1:55 a.m.
Created at: March 4, 2026, 7:41 p.m.