Triple
T19704594
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Myrtha |
E473179
|
entity |
| Predicate | isQueenOf |
P137009
|
FINISHED |
| Object | the Wilis |
—
|
NE NERFINISHED |
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 Wilis | Statement: [Myrtha, isQueenOf, the Wilis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: the Wilis Context triple: [Myrtha, isQueenOf, the Wilis]
-
A.
Weenen
Weenen is a small historic town in KwaZulu-Natal, South Africa, known for its agricultural surroundings and proximity to the Weenen Game Reserve.
-
B.
Wendigo
The Wendigo is a cannibalistic, malevolent spirit or creature from Algonquian folklore, often depicted as a gaunt, monstrous being driven by insatiable hunger.
-
C.
Neszmély
Neszmély is a village in northwestern Hungary on the Danube River, historically noted as the place where Holy Roman Emperor Albert II died.
-
D.
Viy
Viy is a horror novella by Nikolai Gogol, centered on a terrifying demonic figure, that appears as one of the tales in his collection "Mirgorod."
-
E.
Toten
Toten is a traditional rural district in eastern Norway known for its agriculture and scenic landscape, located within Innlandet county.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: the Wilis Target entity description: The Wilis are a spectral sisterhood of vengeful female spirits from the ballet "Giselle," known for forcing men to dance to their deaths under the command of their queen, Myrtha.
-
A.
Weenen
Weenen is a small historic town in KwaZulu-Natal, South Africa, known for its agricultural surroundings and proximity to the Weenen Game Reserve.
-
B.
Wendigo
The Wendigo is a cannibalistic, malevolent spirit or creature from Algonquian folklore, often depicted as a gaunt, monstrous being driven by insatiable hunger.
-
C.
Neszmély
Neszmély is a village in northwestern Hungary on the Danube River, historically noted as the place where Holy Roman Emperor Albert II died.
-
D.
Viy
Viy is a horror novella by Nikolai Gogol, centered on a terrifying demonic figure, that appears as one of the tales in his collection "Mirgorod."
-
E.
Toten
Toten is a traditional rural district in eastern Norway known for its agriculture and scenic landscape, located within Innlandet county.
- F. None of above. chosen
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isQueenOf Context triple: [Myrtha, isQueenOf, the Wilis]
-
A.
chiefQueen
Indicates that one entity is the primary or highest-ranking queen in relation to another entity.
-
B.
royalMistressOf
Indicates that one person is the (typically unofficial) romantic or sexual partner of a royal figure, such as a king or prince.
-
C.
monarchSheIsHeirTo
Indicates that the subject is the designated heir to the specified monarch’s throne or title.
-
D.
monarchMother
Indicates that one entity is the mother of another entity who holds or held a monarchical position (such as king, queen, emperor, etc.).
-
E.
marriedToWidowedQueenOf
Indicates that one entity is married to a person who is the widowed queen of another specified entity (typically a realm or ruler).
- F. None of above. chosen
Provenance (4 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_69d8e516dd048190a0b6c93ea3e71f58 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e642b998608190a82f23bbf77f7bd2 |
completed | April 20, 2026, 3:14 p.m. |
| PD | Predicate disambiguation | batch_69e530438c60819082364c7be3eef6f0 |
completed | April 19, 2026, 7:42 p.m. |
| PDg | Predicate description generation | batch_69e532bbedf081908d801600e2af94a7 |
completed | April 19, 2026, 7:53 p.m. |
Created at: April 10, 2026, 1:46 p.m.