Triple

T134893
Position Surface form Disambiguated ID Type / Status
Subject Scottish Islands E2726 entity
Predicate hasPart P35 FINISHED
Object Canna
Canna is a small, historically rich island in Scotland’s Inner Hebrides, known for its wildlife, archaeological sites, and ownership by the National Trust for Scotland.
 E15003 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: Canna | Statement: [Scottish Islands, hasPart, Canna]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Canna
Context triple: [Scottish Islands, hasPart, Canna]
  • A. Cannabis
    Cannabis is a genus of flowering plants best known for producing psychoactive and medicinal compounds such as THC and CBD, widely used for recreational, therapeutic, and industrial (hemp) purposes.
  • B. Urtica
    Urtica is a genus of herbaceous plants best known for its stinging nettles, which have tiny hairs that can irritate the skin.
  • C. Cresco
    Cresco is a small city in northeastern Iowa known for its agricultural community and historic architecture.
  • D. Tebu
    Tebu is a Saharan ethnic group and language community primarily inhabiting parts of southern Libya, Chad, and Niger.
  • E. Lupinus
    Lupinus is a large genus of flowering plants in the legume family, commonly known as lupines, noted for their tall, colorful flower spikes and nitrogen-fixing ability.
  • 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: Canna
Triple: [Scottish Islands, hasPart, Canna]
Generated description
Canna is a small, historically rich island in Scotland’s Inner Hebrides, known for its wildlife, archaeological sites, and ownership by the National Trust for Scotland.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Canna
Target entity description: Canna is a small, historically rich island in Scotland’s Inner Hebrides, known for its wildlife, archaeological sites, and ownership by the National Trust for Scotland.
  • A. Cannabis
    Cannabis is a genus of flowering plants best known for producing psychoactive and medicinal compounds such as THC and CBD, widely used for recreational, therapeutic, and industrial (hemp) purposes.
  • B. Urtica
    Urtica is a genus of herbaceous plants best known for its stinging nettles, which have tiny hairs that can irritate the skin.
  • C. Cresco
    Cresco is a small city in northeastern Iowa known for its agricultural community and historic architecture.
  • D. Tebu
    Tebu is a Saharan ethnic group and language community primarily inhabiting parts of southern Libya, Chad, and Niger.
  • E. Lupinus
    Lupinus is a large genus of flowering plants in the legume family, commonly known as lupines, noted for their tall, colorful flower spikes and nitrogen-fixing ability.
  • 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_69a2520c0f3481908b0ed054a2fca8d0 completed Feb. 28, 2026, 2:25 a.m.
NER Named-entity recognition batch_69a257a3ad908190b6a8652f09ae0cbb completed Feb. 28, 2026, 2:49 a.m.
NED1 Entity disambiguation (via context triple) batch_69a2aa47e780819083237393f19a0fce completed Feb. 28, 2026, 8:41 a.m.
NEDg Description generation batch_69a2ab56ab4881909e570e9b404bf2fe completed Feb. 28, 2026, 8:46 a.m.
NED2 Entity disambiguation (via description) batch_69a2ab8e01448190b58b2747b7fda5cb completed Feb. 28, 2026, 8:47 a.m.
Created at: Feb. 28, 2026, 2:30 a.m.