Triple

T16682024
Position Surface form Disambiguated ID Type / Status
Subject Cook Strait region E405362 entity
Predicate containsIsland P970 FINISHED
Object Mana Island
Mana Island is a small, predator-free wildlife sanctuary off the southwest coast of New Zealand’s North Island, renowned for its conservation of rare native species and restored coastal ecosystems.
E1960253 NE FINISHED

How this triple was built (2 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: Mana Island | Statement: [Cook Strait region, containsIsland, Mana Island]
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: Mana Island
Triple: [Cook Strait region, containsIsland, Mana Island]
Generated description
Mana Island is a small, predator-free wildlife sanctuary off the southwest coast of New Zealand’s North Island, renowned for its conservation of rare native species and restored coastal ecosystems.

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_69d8838c28748190b3f5967c743940ab completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e37d7018448190b3cb23191322044e completed April 18, 2026, 12:47 p.m.
NED1 Entity disambiguation (via context triple) batch_6a2ad20b27fc8190a09e471de8baa4ae completed June 11, 2026, 3:19 p.m.
NEDg Description generation batch_6a2ad2dffa0c819094a5fe98e9f493dc completed June 11, 2026, 3:23 p.m.
NED2 Entity disambiguation (via description) batch_6a2ae095f2e4819092a90aa55fed57c4 completed June 11, 2026, 4:21 p.m.
Created at: April 10, 2026, 5:19 a.m.