Triple

T4180293
Position Surface form Disambiguated ID Type / Status
Subject SS Canberra E86577 entity
Predicate operator P179 FINISHED
Object P&O
P&O is a historic British shipping and logistics company best known for its passenger liners and ferry services.
 E232409 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: P&O | Statement: [SS Canberra, operator, P&O]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: P&O
Context triple: [SS Canberra, operator, P&O]
  • A. P&O Ferries
    P&O Ferries is a major British ferry operator providing passenger and freight services across routes in the United Kingdom and Europe.
  • B. Cunard Line
    Cunard Line is a historic British shipping company best known for operating famous transatlantic ocean liners and modern cruise ships.
  • C. Isle of Man Steam Packet Company
    The Isle of Man Steam Packet Company is a long-established ferry operator providing passenger and freight services between the Isle of Man and ports in Great Britain and Ireland.
  • D. Riviera Line
    The Riviera Line is a scenic railway route in Devon, England, running along the coast and serving popular seaside towns between Exeter and Paignton.
  • E. Red Funnel
    Red Funnel is a long-established ferry company operating passenger and vehicle services between the Isle of Wight and mainland 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: P&O
Triple: [SS Canberra, operator, P&O]
Generated description
P&O is a historic British shipping and logistics company best known for its passenger liners and ferry services.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: P&O
Target entity description: P&O is a historic British shipping and logistics company best known for its passenger liners and ferry services.
  • A. P&O Ferries chosen
    P&O Ferries is a major British ferry operator providing passenger and freight services across routes in the United Kingdom and Europe.
  • B. Cunard Line
    Cunard Line is a historic British shipping company best known for operating famous transatlantic ocean liners and modern cruise ships.
  • C. Isle of Man Steam Packet Company
    The Isle of Man Steam Packet Company is a long-established ferry operator providing passenger and freight services between the Isle of Man and ports in Great Britain and Ireland.
  • D. Riviera Line
    The Riviera Line is a scenic railway route in Devon, England, running along the coast and serving popular seaside towns between Exeter and Paignton.
  • E. Red Funnel
    Red Funnel is a long-established ferry company operating passenger and vehicle services between the Isle of Wight and mainland England.
  • F. None of above.

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_69aed93de98c8190ad838ce507b77c8a completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69af0302972c819082f6e1938ed417c4 completed March 9, 2026, 5:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69b589f89f4481909f95d3ca915bac18 completed March 14, 2026, 4:16 p.m.
NEDg Description generation batch_69b58e0446d48190a1fd54bcc72af026 completed March 14, 2026, 4:34 p.m.
NED2 Entity disambiguation (via description) batch_69b58e8d57cc8190a823a7cf3a3f0cdf completed March 14, 2026, 4:36 p.m.
Created at: March 9, 2026, 3:45 p.m.