Triple

T15853735
Position Surface form Disambiguated ID Type / Status
Subject Stranraer Harbour E384402 entity
Predicate servedBy P82 FINISHED
Object Sealink
Sealink was a major British ferry company that operated passenger and vehicle services across the Irish Sea and English Channel during the 20th century.
 E1179436 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: Sealink | Statement: [Stranraer Harbour, servedBy, Sealink]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sealink
Context triple: [Stranraer Harbour, servedBy, Sealink]
  • A. Evergreen Marine
    Evergreen Marine is a major Taiwanese container shipping company known for operating one of the world’s largest fleets of container vessels.
  • B. Aeromar
    Aeromar is a Mexican regional airline that primarily operates domestic and short-haul international flights, with a major operational base in Mexico City.
  • C. Nautica
    Nautica is an American lifestyle brand best known for its nautical-inspired apparel and accessories.
  • D. Jahaz
    Jahaz is an ancient Near Eastern town known from biblical and Moabite inscriptions as a key battle site in the conflicts between Israel and Moab.
  • E. Navadvip
    Navadvip is a historic town in West Bengal, India, renowned as a major center of Gaudiya Vaishnavism and the birthplace of the saint Chaitanya Mahaprabhu.
  • 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: Sealink
Triple: [Stranraer Harbour, servedBy, Sealink]
Generated description
Sealink was a major British ferry company that operated passenger and vehicle services across the Irish Sea and English Channel during the 20th century.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sealink
Target entity description: Sealink was a major British ferry company that operated passenger and vehicle services across the Irish Sea and English Channel during the 20th century.
  • A. Evergreen Marine
    Evergreen Marine is a major Taiwanese container shipping company known for operating one of the world’s largest fleets of container vessels.
  • B. Aeromar
    Aeromar is a Mexican regional airline that primarily operates domestic and short-haul international flights, with a major operational base in Mexico City.
  • C. Nautica
    Nautica is an American lifestyle brand best known for its nautical-inspired apparel and accessories.
  • D. Jahaz
    Jahaz is an ancient Near Eastern town known from biblical and Moabite inscriptions as a key battle site in the conflicts between Israel and Moab.
  • E. Navadvip
    Navadvip is a historic town in West Bengal, India, renowned as a major center of Gaudiya Vaishnavism and the birthplace of the saint Chaitanya Mahaprabhu.
  • 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_69d86da422088190aac39e32e6c68429 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e14cae96648190884a85f68b6e9fe1 completed April 16, 2026, 8:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffa14977408190815ef02cc54075cc completed May 9, 2026, 9:04 p.m.
NEDg Description generation batch_69ffa41a86ec8190b46d541965ecf26e completed May 9, 2026, 9:16 p.m.
NED2 Entity disambiguation (via description) batch_69ffa496f3e48190b8dc82bece548aec completed May 9, 2026, 9:18 p.m.
Created at: April 10, 2026, 4:50 a.m.