Triple

T22687738
Position Surface form Disambiguated ID Type / Status
Subject Fashioner of Mankind E560962 entity
Predicate relatesToMyth P137609 FINISHED
Object myths of human creation by Khnum LITERAL FINISHED

How this triple was built (2 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: myths of human creation by Khnum | Statement: [Fashioner of Mankind, relatesToMyth, myths of human creation by Khnum]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: relatesToMyth
Context triple: [Fashioner of Mankind, relatesToMyth, myths of human creation by Khnum]
  • A. linkedToMythology
    Indicates that something has a connection or association with a mythological tradition, figure, story, or theme.
  • B. mythologicalContent chosen
    Indicates that the subject contains, references, or is associated with myths, mythological narratives, or myth-based elements.
  • C. sharesMythosWith
    Indicates that two entities are associated with, or originate from, the same mythological tradition, narrative system, or shared set of myths.
  • D. mythologicalCategory
    Indicates that one entity is classified as belonging to the mythological type, group, or category represented by the other entity.
  • E. subsequentMythology
    Indicates that one mythology develops later than, or is derived from, another mythology in time or tradition.
  • F. None of above.

Provenance (3 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_69e2454d71b48190a1f80af9f82b6fcf completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f178983fc8819080aa00e45ff77952 completed April 29, 2026, 3:18 a.m.
PD Predicate disambiguation batch_69ee62b2259c819091ed1387a748b9f3 completed April 26, 2026, 7:08 p.m.
Created at: April 17, 2026, 3:13 p.m.