Triple

T23941397
Position Surface form Disambiguated ID Type / Status
Subject King George Sound E602790 entity
Predicate hasFeature P182 FINISHED
Object Michaelmas Island
Michaelmas Island is a small, rugged island located within King George Sound off the southern coast of Western Australia, known for its natural coastal scenery and seabird habitats.
E1635196 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: Michaelmas Island | Statement: [King George Sound, hasFeature, Michaelmas 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: Michaelmas Island
Triple: [King George Sound, hasFeature, Michaelmas Island]
Generated description
Michaelmas Island is a small, rugged island located within King George Sound off the southern coast of Western Australia, known for its natural coastal scenery and seabird habitats.

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_69e2953cf6e081909b8e25a10a52dddc completed April 17, 2026, 8:17 p.m.
NER Named-entity recognition batch_69f1d02a1b308190a2d101774b455417 completed April 29, 2026, 9:32 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0fe33689f0819099715d5697a71e1a completed May 22, 2026, 5:01 a.m.
NEDg Description generation batch_6a0fe4f9f0448190bbd9e0b860335482 completed May 22, 2026, 5:09 a.m.
NED2 Entity disambiguation (via description) batch_6a0fe620e40c81909973369ffb8e9dfc completed May 22, 2026, 5:14 a.m.
Created at: April 17, 2026, 9:09 p.m.