Triple

T32655639
Position Surface form Disambiguated ID Type / Status
Subject Hunting Aircraft E834853 entity
Predicate product P490 FINISHED
Object Hunting Percival Provost
The Hunting Percival Provost is a British postwar basic trainer aircraft used primarily by the Royal Air Force for pilot instruction.
 E2016817 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: Hunting Percival Provost | Statement: [Hunting Aircraft, product, Hunting Percival Provost]
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: Hunting Percival Provost
Triple: [Hunting Aircraft, product, Hunting Percival Provost]
Generated description
The Hunting Percival Provost is a British postwar basic trainer aircraft used primarily by the Royal Air Force for pilot instruction.

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_69f3492f72248190ba42fa596aea50e1 completed April 30, 2026, 12:21 p.m.
NER Named-entity recognition batch_69f6c77b504c8190aa225fad8f2cb2aa completed May 3, 2026, 3:56 a.m.
NED1 Entity disambiguation (via context triple) batch_6a3492ad7a488190b499fc491a1fbc6c completed June 19, 2026, 12:51 a.m.
NEDg Description generation batch_6a34938a58dc8190ab8e23d0b021db8b completed June 19, 2026, 12:55 a.m.
NED2 Entity disambiguation (via description) batch_6a34941dcdbc8190b6549f9be8eb672f completed June 19, 2026, 12:58 a.m.
Created at: May 1, 2026, 1:08 a.m.