Triple

T17360370
Position Surface form Disambiguated ID Type / Status
Subject British Columbia coast E422051 entity
Predicate majorCityOnCoast P2994 FINISHED
Object Victoria NE ONDG

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: Victoria | Statement: [British Columbia coast, majorCityOnCoast, Victoria]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Victoria
Context triple: [British Columbia coast, majorCityOnCoast, Victoria]
  • A. Victoria
    Victoria is a coastal municipality in the province of Northern Samar in the Philippines, known for its rural communities and agricultural economy.
  • B. Victoria
    Victoria is a vengeful vampire antagonist from the Twilight series who relentlessly hunts Bella Swan and opposes the Cullen family.
  • C. Victoria
    Victoria is a British historical drama television series that chronicles the early life and reign of Queen Victoria.
  • D. Victoria
    Victoria was a German princess of Saxe-Coburg-Saalfeld best known as the mother of Queen Victoria of the United Kingdom.
  • E. Victoria
    Victoria is the birth name of American actress and model Tanya Roberts, known for her roles in "Charlie's Angels" and the James Bond film "A View to a Kill."
  • 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: Victoria
Triple: [British Columbia coast, majorCityOnCoast, Victoria]
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Victoria
Target entity description: Victoria is the capital city of the Canadian province of British Columbia, known for its historic architecture, mild coastal climate, and vibrant tourism industry.
  • A. Victoria chosen
    Victoria is a coastal city on the southern tip of Vancouver Island known for its historic architecture, mild climate, and vibrant tourism industry.
  • B. Victoria
    Victoria is a major city in southeastern Australia and the capital of the state of Victoria, known for its rich cultural scene, historic architecture, and status as a key economic and population center.
  • C. Victoria
    Victoria is a southeastern Australian state known for its capital city Melbourne, cultural diversity, and varied landscapes ranging from coastal regions to alpine areas.
  • D. Victoria
    Victoria is a central London district known for its major transport hub, theatres, offices, and proximity to landmarks like Buckingham Palace.
  • E. Victoria
    Victoria is a riverside city in the Argentine province of Entre Ríos, known for its historic architecture and proximity to the Paraná River delta.
  • F. None of above.

Provenance (4 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_69d889d520008190a26917a95bf1c2ea completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e43a4cacd881909fd722068b019f25 completed April 19, 2026, 2:13 a.m.
NED1 Entity disambiguation (via context triple) batch_6a01954afb088190a92a0f32f901f13f completed May 11, 2026, 8:37 a.m.
NEDg Description generation batch_6a01962ae4848190b2aad8e19bf6522f in_progress May 11, 2026, 8:41 a.m.
Created at: April 10, 2026, 5:44 a.m.