Triple

T32110487
Position Surface form Disambiguated ID Type / Status
Subject Hole in the Rock (Motukōkako) E820104 entity
Predicate hasName P744 FINISHED
Object Hole in the Rock
Hole in the Rock is a famous natural sea arch and tourist attraction located on Motukōkako Island off the coast of New Zealand’s Bay of Islands.
E1994004 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: Hole in the Rock | Statement: [Hole in the Rock (Motukōkako), hasName, Hole in the Rock]
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: Hole in the Rock
Triple: [Hole in the Rock (Motukōkako), hasName, Hole in the Rock]
Generated description
Hole in the Rock is a famous natural sea arch and tourist attraction located on Motukōkako Island off the coast of New Zealand’s Bay of Islands.

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_69f3490209c881908ec0241476715f15 completed April 30, 2026, 12:20 p.m.
NER Named-entity recognition batch_69f6b69f49d881909de19dec9c5459c5 completed May 3, 2026, 2:44 a.m.
NED1 Entity disambiguation (via context triple) batch_6a2f0123ddb88190af36b6e9178c1250 completed June 14, 2026, 7:29 p.m.
NEDg Description generation batch_6a2f01c288648190bacd6fbdf933732e completed June 14, 2026, 7:32 p.m.
NED2 Entity disambiguation (via description) batch_6a2f033489248190bc282c71f5ad618c completed June 14, 2026, 7:38 p.m.
Created at: May 1, 2026, 12:27 a.m.