Triple

T27052715
Position Surface form Disambiguated ID Type / Status
Subject Speewa Ferry E684817 entity
Predicate connects P390 FINISHED
Object Speewa, New South Wales
Speewa, New South Wales is a small rural locality on the Murray River in southern Australia, known for its cross-border connection to Victoria via the Speewa Ferry.
 E1755754 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: Speewa, New South Wales | Statement: [Speewa Ferry, connects, Speewa, New South Wales]
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: Speewa, New South Wales
Triple: [Speewa Ferry, connects, Speewa, New South Wales]
Generated description
Speewa, New South Wales is a small rural locality on the Murray River in southern Australia, known for its cross-border connection to Victoria via the Speewa Ferry.

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_69ef14829fac8190914bef9ecc3005d7 completed April 27, 2026, 7:47 a.m.
NER Named-entity recognition batch_69f622b145848190b67cfdc47da6a887 completed May 2, 2026, 4:13 p.m.
NED1 Entity disambiguation (via context triple) batch_6a1247f7dd1c819090d3d2d28cf401ce completed May 24, 2026, 12:36 a.m.
NEDg Description generation batch_6a12486c3d048190b11329247c3e8a01 completed May 24, 2026, 12:38 a.m.
NED2 Entity disambiguation (via description) batch_6a1248effb2881909deeccdce34e3b0f completed May 24, 2026, 12:40 a.m.
Created at: April 27, 2026, 8:15 a.m.