Triple

T15281399
Position Surface form Disambiguated ID Type / Status
Subject San Fernando, Trinidad and Tobago E365278 entity
Predicate hasLandmark P105 FINISHED
Object King’s Wharf
King’s Wharf is a historic waterfront area and commercial hub located along the coast of San Fernando, Trinidad and Tobago.
E1148601 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: King’s Wharf | Statement: [San Fernando, Trinidad and Tobago, hasLandmark, King’s Wharf]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: King’s Wharf
Context triple: [San Fernando, Trinidad and Tobago, hasLandmark, King’s Wharf]
  • A. Harbour City
    Harbour City is the nickname of Tema, a major port and industrial city on the Atlantic coast of Ghana.
  • B. Harbour City
    Harbour City is the coastal British Columbia city of Nanaimo, known for its busy port, waterfront, and maritime character.
  • C. Dolphin Quay
    Dolphin Quay is a popular waterfront dining, shopping, and leisure precinct located at the Mandurah Ocean Marina in Western Australia.
  • D. Prince's Wharf
    Prince's Wharf is a historic quay and waterfront area in Bristol, England, known today for housing cultural attractions such as the M Shed museum along the city’s Floating Harbour.
  • E. Mermaid Quay
    Mermaid Quay is a popular leisure and dining complex on the waterfront in Cardiff Bay, featuring restaurants, bars, shops, and views over the marina.
  • 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: King’s Wharf
Triple: [San Fernando, Trinidad and Tobago, hasLandmark, King’s Wharf]
Generated description
King’s Wharf is a historic waterfront area and commercial hub located along the coast of San Fernando, Trinidad and Tobago.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: King’s Wharf
Target entity description: King’s Wharf is a historic waterfront area and commercial hub located along the coast of San Fernando, Trinidad and Tobago.
  • A. Harbour City
    Harbour City is the coastal British Columbia city of Nanaimo, known for its busy port, waterfront, and maritime character.
  • B. Harbour City
    Harbour City is the nickname of Tema, a major port and industrial city on the Atlantic coast of Ghana.
  • C. Dolphin Quay
    Dolphin Quay is a popular waterfront dining, shopping, and leisure precinct located at the Mandurah Ocean Marina in Western Australia.
  • D. Prince's Wharf
    Prince's Wharf is a historic quay and waterfront area in Bristol, England, known today for housing cultural attractions such as the M Shed museum along the city’s Floating Harbour.
  • E. Mermaid Quay
    Mermaid Quay is a popular leisure and dining complex on the waterfront in Cardiff Bay, featuring restaurants, bars, shops, and views over the marina.
  • 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_69d85a103d9081908c1ea6c4c73ac8e3 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e00e51f82081909f63d14b589d5587 completed April 15, 2026, 10:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69feef773bc4819083c9a86543659aa9 completed May 9, 2026, 8:25 a.m.
NEDg Description generation batch_69fef1f731808190957aaa88a86b194c completed May 9, 2026, 8:36 a.m.
NED2 Entity disambiguation (via description) batch_69fef37d1b7081908c5b1be109f590d9 completed May 9, 2026, 8:42 a.m.
Created at: April 10, 2026, 3:15 a.m.