Triple
T8441080
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thor |
E199352
|
entity |
| Predicate | chariotPulledBy |
P20348
|
FINISHED |
| Object | Tanngnjóstr |
E292273
|
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: Tanngnjóstr | Statement: [Thor, chariotPulledBy, Tanngnjóstr]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tanngnjóstr Context triple: [Thor, chariotPulledBy, Tanngnjóstr]
-
A.
Tanngnjóstr
chosen
Tanngnjóstr is one of Thor’s two mythic goats in Norse mythology, known for pulling his chariot and being repeatedly slaughtered and resurrected.
-
B.
Glámr
Glámr is a fearsome undead shepherd and one of the most notorious revenants in the Icelandic Grettis saga, whose haunting leads to the hero Grettir’s famed ghost-fight.
-
C.
Tindhólmur
Tindhólmur is a dramatic, steep-sided islet in the Faroe Islands known for its distinctive five-peaked silhouette rising sharply from the sea near Vágar.
-
D.
Slættaratindur
Slættaratindur is the highest mountain in the Faroe Islands, known for its panoramic views over the surrounding North Atlantic landscape.
-
E.
Gleipnir
Gleipnir is the magically forged, deceptively thin binding in Norse mythology that successfully restrains the monstrous wolf Fenrir.
- 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_69ca8314cd6c8190a6b8c2a1096e18f3 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe138a94081908e306d22aaa39b24 |
completed | March 31, 2026, 2:59 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce1d9ab3a88190ada7741cf054fc1b |
completed | April 2, 2026, 7:41 a.m. |
Created at: March 30, 2026, 6:08 p.m.