Triple
T15203124
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nanna |
E363315
|
entity |
| Predicate | givesGiftTo |
P27470
|
FINISHED |
| Object | Fulla |
E372406
|
NE 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: Fulla | Statement: [Nanna, givesGiftTo, Fulla]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fulla Context triple: [Nanna, givesGiftTo, Fulla]
-
A.
Fulla
chosen
Fulla is a minor Norse goddess associated with Frigg, known for her long flowing hair, golden headband, and role as a trusted handmaiden and keeper of secrets among the Aesir.
-
B.
Finnboda
Finnboda is a waterfront district in Nacka, Sweden, known for its former shipyard area now redeveloped into a residential and commercial neighborhood overlooking central Stockholm.
-
C.
Svanhildr
Svanhildr is a tragic heroine of Norse legend, famed as the beautiful daughter of Sigurd and Gudrun whose violent death sparks the vengeance recounted in the Eddic poem *Hamðismál*.
-
D.
Hjördis
Hjördis is a Scandinavian feminine given name, most notably borne by Swedish model and actress Hjördis Genberg.
-
E.
Vikna
Vikna is a coastal municipality in Trøndelag county, Norway, known for its archipelago of islands, fishing communities, and maritime heritage.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d85a0b78bc8190b6e5ad51a2c4cfc5 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e006b693a48190a6230b7b52bc8cd3 |
completed | April 15, 2026, 9:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fed3390b708190b10c876c437c72c8 |
completed | May 9, 2026, 6:24 a.m. |
Created at: April 10, 2026, 3:10 a.m.