Triple

T579432
Position Surface form Disambiguated ID Type / Status
Subject Norse mythology E15025 entity
Predicate hasDeity P5606 FINISHED
Object Loki
Loki is a trickster god in Norse mythology known for his shape-shifting, cunning, and role in both aiding and undermining the other gods.
E72964 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: Loki | Statement: [Norse mythology, hasDeity, Loki]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Loki
Context triple: [Norse mythology, hasDeity, Loki]
  • A. Heimdall
    Heimdall is a powerful Asgardian guardian in the Marvel universe, known for his all-seeing vision, immense strength, and duty to watch over the Bifröst Bridge.
  • B. Odin
    Odin is the chief god in Norse mythology, associated with wisdom, war, poetry, and magic, and revered as the ruler of Asgard and the Aesir gods.
  • C. Gunnar
    Gunnar is a masculine given name of Old Norse origin, commonly used in Scandinavian countries and associated with warriors or bold fighters.
  • D. Hawkeye
    Hawkeye is a Marvel Cinematic Universe Disney+ series centered on the archer superhero Clint Barton and his protégé Kate Bishop.
  • E. Svante
    Svante is the given name of Swedish geneticist Svante Pääbo, a Nobel Prize–winning pioneer in the field of paleogenomics.
  • 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: Loki
Triple: [Norse mythology, hasDeity, Loki]
Generated description
Loki is a trickster god in Norse mythology known for his shape-shifting, cunning, and role in both aiding and undermining the other gods.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Loki
Target entity description: Loki is a trickster god in Norse mythology known for his shape-shifting, cunning, and role in both aiding and undermining the other gods.
  • A. Heimdall
    Heimdall is a powerful Asgardian guardian in the Marvel universe, known for his all-seeing vision, immense strength, and duty to watch over the Bifröst Bridge.
  • B. Odin
    Odin is the chief god in Norse mythology, associated with wisdom, war, poetry, and magic, and revered as the ruler of Asgard and the Aesir gods.
  • C. Gunnar
    Gunnar is a masculine given name of Old Norse origin, commonly used in Scandinavian countries and associated with warriors or bold fighters.
  • D. Hawkeye
    Hawkeye is a Marvel Cinematic Universe Disney+ series centered on the archer superhero Clint Barton and his protégé Kate Bishop.
  • E. Svante
    Svante is the given name of Swedish geneticist Svante Pääbo, a Nobel Prize–winning pioneer in the field of paleogenomics.
  • 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_69a4935783b8819082b77726ec10cc42 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a49b6c358081908f458b9e3e208c0d completed March 1, 2026, 8:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69a508a025308190ac35a5e3606de4de completed March 2, 2026, 3:48 a.m.
NEDg Description generation batch_69a5090f5450819098324292a444fd94 completed March 2, 2026, 3:50 a.m.
NED2 Entity disambiguation (via description) batch_69a509facafc819089838e0724656ea0 completed March 2, 2026, 3:54 a.m.
Created at: March 1, 2026, 7:33 p.m.