Triple

T20989381
Position Surface form Disambiguated ID Type / Status
Subject Magnus the Good E516977 entity
Predicate nickname P55 FINISHED
Object the Good
The Good is the epithet of Magnus I, a medieval king of Norway and Denmark remembered for his just and capable rule.
 E1460989 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: the Good | Statement: [Magnus the Good, nickname, the Good]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: the Good
Context triple: [Magnus the Good, nickname, the Good]
  • A. the Good
    The Good is the honorific epithet of Byzantine emperor John II Komnenos, reflecting his reputation for piety, justice, and capable rule.
  • B. On the Good
    "On the Good" is a lost philosophical treatise by the Middle Platonist Numenius of Apamea that explored the nature of the supreme Good and significantly influenced later Neoplatonic thought.
  • C. Gutes
    The Gutes were the North Germanic inhabitants of the Baltic island of Gotland, known for their distinct Gutnish language and extensive Viking Age trade networks.
  • D. Good and Evil
    Good and Evil is a philosophical work by Martin Buber that explores the nature of morality, human freedom, and the ethical dimensions of good and evil in human relationships.
  • E. Good and Evil
    "Good and Evil" is a song by Japanese singer Rei Momo.
  • 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: the Good
Triple: [Magnus the Good, nickname, the Good]
Generated description
The Good is the epithet of Magnus I, a medieval king of Norway and Denmark remembered for his just and capable rule.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: the Good
Target entity description: The Good is the epithet of Magnus I, a medieval king of Norway and Denmark remembered for his just and capable rule.
  • A. the Good
    The Good is the honorific epithet of Byzantine emperor John II Komnenos, reflecting his reputation for piety, justice, and capable rule.
  • B. On the Good
    "On the Good" is a lost philosophical treatise by the Middle Platonist Numenius of Apamea that explored the nature of the supreme Good and significantly influenced later Neoplatonic thought.
  • C. Gutes
    The Gutes were the North Germanic inhabitants of the Baltic island of Gotland, known for their distinct Gutnish language and extensive Viking Age trade networks.
  • D. Good and Evil
    "Good and Evil" is a song by Japanese singer Rei Momo.
  • E. Good and Evil
    Good and Evil is a philosophical work by Martin Buber that explores the nature of morality, human freedom, and the ethical dimensions of good and evil in human relationships.
  • 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_69e0b4ffac148190bbade9f0eceb660b completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6fbe5f49c8190a5c031eceba9ebf7 completed April 21, 2026, 4:24 a.m.
NED1 Entity disambiguation (via context triple) batch_6a092fc9905c81909b42a0bd6ab59fef completed May 17, 2026, 3:02 a.m.
NEDg Description generation batch_6a09316d8a5081909bd21ea01422be47 completed May 17, 2026, 3:09 a.m.
NED2 Entity disambiguation (via description) batch_6a0932384acc8190a4d2cbdc208d4969 completed May 17, 2026, 3:12 a.m.
Created at: April 16, 2026, 1:49 p.m.