Triple

T37592772
Position Surface form Disambiguated ID Type / Status
Subject Beasain E935299 entity
Predicate hasRailwayManufacturingHeritage P2411 FINISHED
Object CAF workshops
CAF workshops are major railway manufacturing and maintenance facilities operated by the Spanish rolling stock company CAF, known for producing and servicing trains and related equipment.
E59649 NE FINISHED

How this triple was built (3 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: CAF workshops | Statement: [Beasain, hasRailwayManufacturingHeritage, CAF workshops]
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: CAF workshops
Triple: [Beasain, hasRailwayManufacturingHeritage, CAF workshops]
Generated description
CAF workshops are major railway manufacturing and maintenance facilities operated by the Spanish rolling stock company CAF, known for producing and servicing trains and related equipment.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasRailwayManufacturingHeritage
Context triple: [Beasain, hasRailwayManufacturingHeritage, CAF workshops]
  • A. hasIndustrialHeritage chosen
    Indicates that an entity possesses or is associated with historically significant industrial sites, structures, or practices.
  • B. railwayHeritageFrom
    Indicates that something derives its historical or cultural significance from a particular railway or railway-related source.
  • C. hasRailroadHistory
    Indicates that an entity is associated with, involved in, or notable for historical events, operations, or developments related to railroads.
  • D. hasRailroadHistoryWith
    Indicates a historical relationship or connection between entities involving railroads, such as shared development, operation, or significant events in railway history.
  • E. railwayHeritageFeature
    Indicates that something is a feature associated with railway heritage, such as historically significant railway structures, equipment, or related elements.
  • F. None of above.

Provenance (6 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_69f76ecf39c081909baffe597bb55273 completed May 3, 2026, 3:50 p.m.
NER Named-entity recognition batch_69fe0d165a48819098b854318a50d76c completed May 8, 2026, 4:19 p.m.
NED1 Entity disambiguation (via context triple) batch_6a40a800a918819081ad0e2943ad0cfd completed June 28, 2026, 4:50 a.m.
NEDg Description generation batch_6a40a9675434819092d1606edfa90482 completed June 28, 2026, 4:56 a.m.
NED2 Entity disambiguation (via description) batch_6a40a9ffe2688190ad8c76e103b9eace completed June 28, 2026, 4:58 a.m.
PD Predicate disambiguation batch_69fe0931002481908a95b34f95e9f64e completed May 8, 2026, 4:02 p.m.
Created at: May 3, 2026, 4:18 p.m.