Triple

T23695880
Position Surface form Disambiguated ID Type / Status
Subject British Rail Class 143 E585443 entity
Predicate bodyworkBy P153436 FINISHED
Object Walter Alexander
Walter Alexander was a prominent Scottish bus and coach bodybuilder known for manufacturing vehicle bodies for public transport operators across the UK.
 E1607222 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: Walter Alexander | Statement: [British Rail Class 143, bodyworkBy, Walter Alexander]
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: Walter Alexander
Triple: [British Rail Class 143, bodyworkBy, Walter Alexander]
Generated description
Walter Alexander was a prominent Scottish bus and coach bodybuilder known for manufacturing vehicle bodies for public transport operators across the UK.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: bodyworkBy
Context triple: [British Rail Class 143, bodyworkBy, Walter Alexander]
  • A. bodyTreatment
    Indicates a treatment or therapeutic procedure that is applied to a person's body.
  • B. bodyNumber
    Indicates the numerical position or identifier assigned to a body within a sequence or collection of bodies.
  • C. oreBody
    Indicates that one entity is an ore body, i.e., a naturally occurring concentration of minerals in the context of the other entity.
  • D. materialWorked
    Indicates that an agent performs work or processing on a specified material.
  • E. bodyWall
    Indicates that one entity serves as the body wall or outer structural boundary enclosing another entity.
  • F. None of above. chosen

Provenance (7 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_69e24904bd508190abfcb74855de2918 completed April 17, 2026, 2:51 p.m.
NER Named-entity recognition batch_69f1b5c65ab88190be59a8fb731cf030 completed April 29, 2026, 7:39 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0f75fd9ab88190a69c87c81aaaa0c3 completed May 21, 2026, 9:15 p.m.
NEDg Description generation batch_6a0f76a8397081909ddde2410c127208 completed May 21, 2026, 9:18 p.m.
NED2 Entity disambiguation (via description) batch_6a0f77e88a4c819099511cdcf7357ab7 completed May 21, 2026, 9:23 p.m.
PD Predicate disambiguation batch_69f155d5265881908e43a9696b6a6d0f completed April 29, 2026, 12:50 a.m.
PDg Predicate description generation batch_69f157cc43a881909ed2d8b0a09b5d73 completed April 29, 2026, 12:58 a.m.
Created at: April 17, 2026, 6:52 p.m.