Triple

T8597756
Position Surface form Disambiguated ID Type / Status
Subject River Tavy E203593 entity
Predicate flowsThrough P225 FINISHED
Object Peter Tavy
Peter Tavy is a small rural village and civil parish on the western edge of Dartmoor in Devon, England.
 E744709 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: Peter Tavy | Statement: [River Tavy, flowsThrough, Peter Tavy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Peter Tavy
Context triple: [River Tavy, flowsThrough, Peter Tavy]
  • A. William Tailer
    William Tailer was an early 18th-century colonial politician who briefly served as acting governor of the Province of Massachusetts Bay.
  • B. Matthew Mott
    Matthew Mott is an Australian cricket coach best known for leading successful limited-overs sides, including national teams in white-ball formats.
  • C. Lou Barle
    Lou Barle was a professional basketball player best known for his time with the early National Basketball League team the Oshkosh All-Stars.
  • D. Robert Taffy
    Robert Taffy was the architect responsible for designing Mapo Hall, a historic colonial-era civic building in Ibadan, Nigeria.
  • E. Thomas Nevile
    Thomas Nevile was a prominent English clergyman and academic of the late 16th and early 17th centuries, best known for his role as Master of Trinity College, Cambridge, and for overseeing major architectural developments there.
  • 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: Peter Tavy
Triple: [River Tavy, flowsThrough, Peter Tavy]
Generated description
Peter Tavy is a small rural village and civil parish on the western edge of Dartmoor in Devon, England.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Peter Tavy
Target entity description: Peter Tavy is a small rural village and civil parish on the western edge of Dartmoor in Devon, England.
  • A. William Tailer
    William Tailer was an early 18th-century colonial politician who briefly served as acting governor of the Province of Massachusetts Bay.
  • B. Matthew Mott
    Matthew Mott is an Australian cricket coach best known for leading successful limited-overs sides, including national teams in white-ball formats.
  • C. Lou Barle
    Lou Barle was a professional basketball player best known for his time with the early National Basketball League team the Oshkosh All-Stars.
  • D. Robert Taffy
    Robert Taffy was the architect responsible for designing Mapo Hall, a historic colonial-era civic building in Ibadan, Nigeria.
  • E. Thomas Nevile
    Thomas Nevile was a prominent English clergyman and academic of the late 16th and early 17th centuries, best known for his role as Master of Trinity College, Cambridge, and for overseeing major architectural developments there.
  • 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_69ca832b56948190ba751cec255308f1 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cc46cacbe88190b95beeedc9f480b0 completed March 31, 2026, 10:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69cea8dd86d08190a7f8e674e16dd8b6 completed April 2, 2026, 5:35 p.m.
NEDg Description generation batch_69cea9d0dad0819095134f6f8cafb4c0 completed April 2, 2026, 5:39 p.m.
NED2 Entity disambiguation (via description) batch_69ceaa7025388190a3f17aca46d4858e completed April 2, 2026, 5:42 p.m.
Created at: March 30, 2026, 6:24 p.m.