Triple

T16035384
Position Surface form Disambiguated ID Type / Status
Subject A Wizard of Earthsea E388957 entity
Predicate character P662 FINISHED
Object Vetch
Vetch is a loyal and skilled wizard in Ursula K. Le Guin’s Earthsea series, serving as Ged’s close friend and steadfast companion on his journeys.
E1190604 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: Vetch | Statement: [A Wizard of Earthsea, character, Vetch]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vetch
Context triple: [A Wizard of Earthsea, character, Vetch]
  • A. Vetch
    Vetch is a surname most notably associated with Samuel Vetch, a colonial governor of Nova Scotia in the early 18th century.
  • B. Lucerne
    Lucerne is a picturesque Swiss city known for its preserved medieval architecture, lakeside setting on Lake Lucerne, and proximity to the Swiss Alps.
  • C. Lathyrus
    Lathyrus is a genus of flowering plants in the legume family, best known for species like the ornamental sweet pea.
  • D. Caltha
    Caltha is a small genus of marsh-dwelling flowering plants commonly known as marsh marigolds, found in temperate and cold regions of the Northern Hemisphere.
  • E. Parsley Hay
    Parsley Hay is a small hamlet and popular cycling and walking hub in the Peak District National Park, known for its trailhead facilities on former railway routes.
  • 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: Vetch
Triple: [A Wizard of Earthsea, character, Vetch]
Generated description
Vetch is a loyal and skilled wizard in Ursula K. Le Guin’s Earthsea series, serving as Ged’s close friend and steadfast companion on his journeys.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Vetch
Target entity description: Vetch is a loyal and skilled wizard in Ursula K. Le Guin’s Earthsea series, serving as Ged’s close friend and steadfast companion on his journeys.
  • A. Vetch
    Vetch is a surname most notably associated with Samuel Vetch, a colonial governor of Nova Scotia in the early 18th century.
  • B. Lucerne
    Lucerne is a picturesque Swiss city known for its preserved medieval architecture, lakeside setting on Lake Lucerne, and proximity to the Swiss Alps.
  • C. Lathyrus
    Lathyrus is a genus of flowering plants in the legume family, best known for species like the ornamental sweet pea.
  • D. Caltha
    Caltha is a small genus of marsh-dwelling flowering plants commonly known as marsh marigolds, found in temperate and cold regions of the Northern Hemisphere.
  • E. Parsley Hay
    Parsley Hay is a small hamlet and popular cycling and walking hub in the Peak District National Park, known for its trailhead facilities on former railway routes.
  • 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_69d86dada3808190825d5f80d72fbe88 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1833b84608190887dafda5d081dc0 completed April 17, 2026, 12:47 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffdbd3a1248190ad055892cebde5f0 completed May 10, 2026, 1:13 a.m.
NEDg Description generation batch_69ffdc5fd30c8190aaf66482f24285b4 completed May 10, 2026, 1:16 a.m.
NED2 Entity disambiguation (via description) batch_69ffdd0392e08190af42a0cdc5dd4c1f completed May 10, 2026, 1:18 a.m.
Created at: April 10, 2026, 4:56 a.m.