Triple
T26296539
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Io plasma torus |
E661433
|
entity |
| Predicate | trappedBy |
P114541
|
FINISHED |
| Object | Jupiter magnetic field |
—
|
LITERAL 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: Jupiter magnetic field | Statement: [Io plasma torus, trappedBy, Jupiter magnetic field]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: trappedBy Context triple: [Io plasma torus, trappedBy, Jupiter magnetic field]
-
A.
trappedIn
chosen
Indicates that one entity is confined or caught within another entity or bounded space, unable to leave freely.
-
B.
trappedDuring
Indicates that one entity is confined, caught, or immobilized while a specified event or situation is occurring.
-
C.
caughtBetween
Indicates being simultaneously subject to opposing forces, demands, or sides, unable to fully align with or escape either.
-
D.
trap
Indicates that an entity captures, confines, or ensnares another entity, typically preventing its escape or movement.
-
E.
heldCaptive
Indicates that one entity is being forcibly confined or restrained by another, preventing their freedom of movement or escape.
- F. None of above.
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_69ee812cd48c81908054068f545f0526 |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69f60eaea1d08190b93b85590b8c9781 |
completed | May 2, 2026, 2:48 p.m. |
| PD | Predicate disambiguation | batch_69f5f7ff548c8190a23e98c5e66e0bc7 |
completed | May 2, 2026, 1:11 p.m. |
Created at: April 26, 2026, 10:12 p.m.