Triple
T37418611
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Milky Way bulge and bar |
E929784
|
entity |
| Predicate | funnels |
P174130
|
FINISHED |
| Object | gas toward the Galactic center |
—
|
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: gas toward the Galactic center | Statement: [Milky Way bulge and bar, funnels, gas toward the Galactic center]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: funnels Context triple: [Milky Way bulge and bar, funnels, gas toward the Galactic center]
-
A.
numberOfFunnels
Indicates the quantity of funnels associated with or present on a given entity.
-
B.
hasFunnels
Indicates that one entity possesses or is equipped with one or more funnels associated with another entity or context.
-
C.
flowsVia
chosen
Indicates that something (such as a substance, signal, or current) moves or is transmitted along, through, or by means of a specified medium, path, or channel.
-
D.
streamlines
Indicates that one entity makes a process, workflow, or interaction between entities more efficient, simple, or direct.
-
E.
flowsOn
Indicates that one entity (typically a fluid or current) moves continuously along the surface or path defined by another entity.
- 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_69f76ebde49481908566cd96b37ccc84 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fb9e1845e881908d19158440cf3b87 |
completed | May 6, 2026, 8:01 p.m. |
| PD | Predicate disambiguation | batch_69fb8d08d6988190a00794ac26078348 |
completed | May 6, 2026, 6:48 p.m. |
Created at: May 3, 2026, 4:16 p.m.