Triple

T36114950
Position Surface form Disambiguated ID Type / Status
Subject Toyota rally-raid programs E1044593 entity
Predicate notableDriver P2087 FINISHED
Object Henk Lategan
Henk Lategan is a South African rally driver best known for competing at the top level of cross-country and rally-raid events, including the Dakar Rally, with Toyota.
E2173945 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: Henk Lategan | Statement: [Toyota rally-raid programs, notableDriver, Henk Lategan]
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: Henk Lategan
Triple: [Toyota rally-raid programs, notableDriver, Henk Lategan]
Generated description
Henk Lategan is a South African rally driver best known for competing at the top level of cross-country and rally-raid events, including the Dakar Rally, with Toyota.

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_69f76e344a4c8190af3858c6d78ba88f completed May 3, 2026, 3:48 p.m.
NER Named-entity recognition batch_69f7b2cbe27c8190bd777cf24e1fd168 completed May 3, 2026, 8:40 p.m.
NED1 Entity disambiguation (via context triple) batch_6a3934020fd4819096dc08e50c2386e1 completed June 22, 2026, 1:09 p.m.
NEDg Description generation batch_6a393ba086b481909c7747b34c0963f1 completed June 22, 2026, 1:41 p.m.
NED2 Entity disambiguation (via description) batch_6a393c7834848190b6b58e76d41b9d4b completed June 22, 2026, 1:45 p.m.
Created at: May 3, 2026, 4:08 p.m.