Triple

T25019523
Position Surface form Disambiguated ID Type / Status
Subject Pancake Rocks at Punakaiki E626533 entity
Predicate locatedIn P40 FINISHED
Object Punakaiki
Punakaiki is a small coastal settlement on New Zealand’s South Island, famed for its dramatic limestone formations, rugged coastline, and role as a gateway to Paparoa National Park.
E1693878 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: Punakaiki | Statement: [Pancake Rocks at Punakaiki, locatedIn, Punakaiki]
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: Punakaiki
Triple: [Pancake Rocks at Punakaiki, locatedIn, Punakaiki]
Generated description
Punakaiki is a small coastal settlement on New Zealand’s South Island, famed for its dramatic limestone formations, rugged coastline, and role as a gateway to Paparoa National Park.

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_69e2ff28ee3881909c626af002457a4a completed April 18, 2026, 3:48 a.m.
NER Named-entity recognition batch_69f44ba9108c8190aca5c07f277d82b8 completed May 1, 2026, 6:43 a.m.
NED1 Entity disambiguation (via context triple) batch_6a10cbc2a74481909c1e1a51e33ba3b0 completed May 22, 2026, 9:33 p.m.
NEDg Description generation batch_6a10cde4cc7c819082eea238a1e4a786 completed May 22, 2026, 9:43 p.m.
NED2 Entity disambiguation (via description) batch_6a10ce8ce9dc819097e693a12731bf5d completed May 22, 2026, 9:45 p.m.
Created at: April 18, 2026, 6:06 a.m.