Triple

T3270665
Position Surface form Disambiguated ID Type / Status
Subject River Tamar E68638 entity
Predicate nearLandmark P3449 FINISHED
Object Devonport
Devonport is a port city in southwest England, now part of Plymouth, historically known for its major naval dockyard and maritime heritage.
 E348511 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: Devonport | Statement: [River Tamar, nearLandmark, Devonport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Devonport
Context triple: [River Tamar, nearLandmark, Devonport]
  • A. Devonport
    Devonport is a coastal city in northern Tasmania, Australia, known as a key regional port and gateway to the island via the Spirit of Tasmania ferry.
  • B. Weymouth
    Weymouth is a seaside town and popular tourist resort on the south coast of Dorset, England, known for its sandy beach and Georgian seafront.
  • C. Weymouth
    Weymouth is a coastal town in eastern Massachusetts known as one of the state’s oldest settlements and a residential suburb of Boston.
  • D. Plymouth
    Plymouth is a historic coastal town in Massachusetts, United States, best known as the landing site of the Pilgrims and often called "America’s Hometown."
  • E. Plymouth
    Plymouth is the former capital of Montserrat that was destroyed and permanently evacuated following devastating volcanic eruptions in the 1990s.
  • 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: Devonport
Triple: [River Tamar, nearLandmark, Devonport]
Generated description
Devonport is a port city in southwest England, now part of Plymouth, historically known for its major naval dockyard and maritime heritage.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Devonport
Target entity description: Devonport is a port city in southwest England, now part of Plymouth, historically known for its major naval dockyard and maritime heritage.
  • A. Devonport
    Devonport is a coastal city in northern Tasmania, Australia, known as a key regional port and gateway to the island via the Spirit of Tasmania ferry.
  • B. Weymouth
    Weymouth is a seaside town and popular tourist resort on the south coast of Dorset, England, known for its sandy beach and Georgian seafront.
  • C. Weymouth
    Weymouth is a coastal town in eastern Massachusetts known as one of the state’s oldest settlements and a residential suburb of Boston.
  • D. Plymouth
    Plymouth is a historic coastal town in Massachusetts, United States, best known as the landing site of the Pilgrims and often called "America’s Hometown."
  • E. Plymouth
    Plymouth is the former capital of Montserrat that was destroyed and permanently evacuated following devastating volcanic eruptions in the 1990s.
  • 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_69ad859b54f881909bf530d549caf2fd completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adaff349148190beae8c0994b7ad83 completed March 8, 2026, 5:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69b31a698ab08190b558c4ff3f9b27fc completed March 12, 2026, 7:56 p.m.
NEDg Description generation batch_69b31e26b7088190b845a183d32de8bc completed March 12, 2026, 8:12 p.m.
NED2 Entity disambiguation (via description) batch_69b31e7f8c7081908066d5a1c3bce83e completed March 12, 2026, 8:13 p.m.
Created at: March 8, 2026, 3:09 p.m.