Triple
T23301329
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ragnar Lodbrok |
E590311
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Lagertha |
—
|
NE NERFINISHED |
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: Lagertha | Statement: [Ragnar Lodbrok, spouse, Lagertha]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lagertha Context triple: [Ragnar Lodbrok, spouse, Lagertha]
-
A.
Lagertha
chosen
Lagertha is a legendary Viking shield-maiden and warrior, prominently featured as a central character in the historical drama series "Vikings."
-
B.
Eivor Varinsdottir
Eivor Varinsdottir is the Viking warrior protagonist of Assassin's Creed Valhalla, known for leading her clan from Norway to England during the 9th century.
-
C.
Ingrith
Ingrith is a feminine given name, likely a variant of the Scandinavian name Ingrid.
-
D.
Gunnhild
Gunnhild was the mother of King Sverre of Norway, a key figure in the country’s medieval royal lineage.
-
E.
Gunnhildr
Gunnhildr is a powerful and scheming Norwegian queen, often portrayed as an antagonist to the Icelandic hero Egill Skallagrímsson in medieval saga literature.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e25d1c0ecc8190a355aa229f06d0e0 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f196d37fd08190ad2d199c54324c02 |
completed | April 29, 2026, 5:27 a.m. |
Created at: April 17, 2026, 5:04 p.m.