Triple

T33689181
Position Surface form Disambiguated ID Type / Status
Subject Kiel–Lübeck railway E863125 entity
Predicate usesRollingStock P5426 FINISHED
Object DB Class 648
The DB Class 648 is a diesel multiple unit train operated by Deutsche Bahn, commonly used for regional passenger services on non-electrified lines in Germany.
 E2063632 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: DB Class 648 | Statement: [Kiel–Lübeck railway, usesRollingStock, DB Class 648]
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: DB Class 648
Triple: [Kiel–Lübeck railway, usesRollingStock, DB Class 648]
Generated description
The DB Class 648 is a diesel multiple unit train operated by Deutsche Bahn, commonly used for regional passenger services on non-electrified lines in Germany.

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_69f3498662b48190904442c39df84fb7 completed April 30, 2026, 12:22 p.m.
NER Named-entity recognition batch_69f6fa6708f88190b8589a41d2271ba6 completed May 3, 2026, 7:33 a.m.
NED1 Entity disambiguation (via context triple) batch_6a363c95d3f08190b696cbdb37ac0128 completed June 20, 2026, 7:09 a.m.
NEDg Description generation batch_6a3645cd6ffc8190a83cbf74c3f3a863 completed June 20, 2026, 7:48 a.m.
NED2 Entity disambiguation (via description) batch_6a36464b786881909f4bff7db82b05f2 completed June 20, 2026, 7:50 a.m.
Created at: May 1, 2026, 1:43 a.m.