Triple

T35987564
Position Surface form Disambiguated ID Type / Status
Subject 2004 World Rally Championship E1040753 entity
Predicate featuredManufacturerTeam P131747 FINISHED
Object Peugeot Total
Peugeot Total is the factory-backed rally team of French automaker Peugeot, known for competing at the top level of the World Rally Championship.
E2164914 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: Peugeot Total | Statement: [2004 World Rally Championship, featuredManufacturerTeam, Peugeot Total]
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: Peugeot Total
Triple: [2004 World Rally Championship, featuredManufacturerTeam, Peugeot Total]
Generated description
Peugeot Total is the factory-backed rally team of French automaker Peugeot, known for competing at the top level of the World Rally Championship.

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_69f76e28293c8190ae3f4e2208b87117 completed May 3, 2026, 3:47 p.m.
NER Named-entity recognition batch_6a03809bd57c8190beb371feaf44a7db completed May 12, 2026, 7:33 p.m.
NED1 Entity disambiguation (via context triple) batch_6a38bfe824b08190810cff02a3bbe883 completed June 22, 2026, 4:54 a.m.
NEDg Description generation batch_6a38c0a8a0908190a845f3f6e7040e1e completed June 22, 2026, 4:57 a.m.
NED2 Entity disambiguation (via description) batch_6a38c164f0e88190bef255d462f21732 completed June 22, 2026, 5 a.m.
Created at: May 3, 2026, 4:07 p.m.