Triple

T15120050
Position Surface form Disambiguated ID Type / Status
Subject DfT category E E361145 entity
Predicate hasAbbreviation P43 FINISHED
Object Category E
Category E is a UK Department for Transport classification used to designate a specific type or grouping within its regulatory or administrative framework.
 E1138298 NE FINISHED

How this triple was built (4 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: Category E | Statement: [DfT category E, hasAbbreviation, Category E]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Category E
Context triple: [DfT category E, hasAbbreviation, Category E]
  • A. EC
    EC is the two-letter ISO 3166-1 alpha-2 country code assigned to Ecuador.
  • B. EC
    EC is a central London postcode area covering much of the historic City of London and parts of the surrounding financial district.
  • C. EC
    EC is the student nickname for MIT’s East Campus undergraduate dormitory, known for its tight-knit, hands-on, and hacker-oriented culture.
  • D. EC
    EC is the standard abbreviation for EuroCity, a network of international express passenger trains operating across various European countries.
  • E. EC
    EC is the commonly used abbreviation for Epsom College, a well-known independent co-educational boarding and day school in Surrey, England.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
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: Category E
Triple: [DfT category E, hasAbbreviation, Category E]
Generated description
Category E is a UK Department for Transport classification used to designate a specific type or grouping within its regulatory or administrative framework.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Category E
Target entity description: Category E is a UK Department for Transport classification used to designate a specific type or grouping within its regulatory or administrative framework.
  • A. EC
    EC is the two-letter ISO 3166-1 alpha-2 country code assigned to Ecuador.
  • B. EC
    EC is a central London postcode area covering much of the historic City of London and parts of the surrounding financial district.
  • C. EC
    EC is the student nickname for MIT’s East Campus undergraduate dormitory, known for its tight-knit, hands-on, and hacker-oriented culture.
  • D. EC
    EC is the abbreviation for the APEC Economic Committee, a body that supports economic policy research and cooperation among APEC member economies.
  • E. EC
    EC is the commonly used abbreviation for Epsom College, a well-known independent co-educational boarding and day school in Surrey, England.
  • F. None of above. chosen

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_69d85a0491ec8190830960be8fafb994 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e0059e036c8190959ff3bde8f2356f completed April 15, 2026, 9:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69feb7f2e3408190ae095d16396e420d completed May 9, 2026, 4:28 a.m.
NEDg Description generation batch_69feb99b6a108190ba389703bc123e17 completed May 9, 2026, 4:35 a.m.
NED2 Entity disambiguation (via description) batch_69feba50cd3c81909c4c14c6a7510dd4 completed May 9, 2026, 4:38 a.m.
Created at: April 10, 2026, 3:06 a.m.