Triple
T1092358
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Orion |
E24193
|
entity |
| Predicate | bestVisibleIn |
P6960
|
FINISHED |
| Object | winter in the Northern Hemisphere |
—
|
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: winter in the Northern Hemisphere | Statement: [Orion, bestVisibleIn, winter in the Northern Hemisphere]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bestVisibleIn Context triple: [Orion, bestVisibleIn, winter in the Northern Hemisphere]
-
A.
visibleAt
Indicates that one entity can be seen or perceived from a specific location, viewpoint, or context at a given time.
-
B.
bestSeenIn
chosen
Indicates that something is most effectively or appropriately experienced, observed, or appreciated within a particular context, medium, or setting.
-
C.
canBeSeenWith
Indicates that two entities are observable together in the same context, setting, or time.
-
D.
availableAs
Indicates that one entity can be used, accessed, or offered in the form, role, or capacity of another entity.
-
E.
presentedIn
Indicates that something is shown, displayed, or formally introduced within a particular context, medium, event, or setting.
- 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_69a49404428c819092dcc9632f5f7b8b |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4b982018481908b222df095e318c0 |
completed | March 1, 2026, 10:11 p.m. |
| PD | Predicate disambiguation | batch_69a4b743175481908f3967e589717c55 |
completed | March 1, 2026, 10:01 p.m. |
Created at: March 1, 2026, 7:42 p.m.