Triple
T7244314
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kalevala |
E156433
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object |
Louhi
Louhi is a powerful and malevolent witch-queen of the land of Pohjola in Finnish mythology, best known as a central antagonist in the national epic Kalevala.
|
E651748
|
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: Louhi | Statement: [Kalevala, mainCharacter, Louhi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Louhi Context triple: [Kalevala, mainCharacter, Louhi]
-
A.
Lohrasp
Lohrasp is a legendary king in Persian mythology, known from the Shahnameh as a ruler of Iran who followed the heroic reigns of earlier Kayanian monarchs.
-
B.
Lihir
Lihir is an Oceanic language spoken primarily on the Lihir Islands of Papua New Guinea.
-
C.
Haukeli
Haukeli is a mountainous village area in southern Norway known as a key transit point and outdoor recreation destination, especially for skiing and hiking.
-
D.
Harku
Harku is a small settlement in northern Estonia located within Harku Parish, near the capital city of Tallinn.
-
E.
Loarki
Loarki is a lesser-known dialect of the Rajasthani language spoken by specific communities in the northwestern Indian subcontinent.
- 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: Louhi Triple: [Kalevala, mainCharacter, Louhi]
Generated description
Louhi is a powerful and malevolent witch-queen of the land of Pohjola in Finnish mythology, best known as a central antagonist in the national epic Kalevala.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Louhi Target entity description: Louhi is a powerful and malevolent witch-queen of the land of Pohjola in Finnish mythology, best known as a central antagonist in the national epic Kalevala.
-
A.
Lohrasp
Lohrasp is a legendary king in Persian mythology, known from the Shahnameh as a ruler of Iran who followed the heroic reigns of earlier Kayanian monarchs.
-
B.
Lihir
Lihir is an Oceanic language spoken primarily on the Lihir Islands of Papua New Guinea.
-
C.
Haukeli
Haukeli is a mountainous village area in southern Norway known as a key transit point and outdoor recreation destination, especially for skiing and hiking.
-
D.
Harku
Harku is a small settlement in northern Estonia located within Harku Parish, near the capital city of Tallinn.
-
E.
Loarki
Loarki is a lesser-known dialect of the Rajasthani language spoken by specific communities in the northwestern Indian subcontinent.
- 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_69c68827b5e481908dc05e145b2c92d4 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6ea58533481909af7a4a6ade40eff |
completed | March 27, 2026, 8:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7d3930f588190a724279dae286d5c |
completed | March 28, 2026, 1:11 p.m. |
| NEDg | Description generation | batch_69c7d4690adc81909abbfb7a756f453d |
completed | March 28, 2026, 1:15 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c7d5137efc81908745cca73b112f0c |
completed | March 28, 2026, 1:18 p.m. |
Created at: March 27, 2026, 2:56 p.m.