Triple
T868892
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Local Bubble |
E18766
|
entity |
| Predicate | gasDensity |
P2023
|
FINISHED |
| Object | much lower than average interstellar medium density |
—
|
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: much lower than average interstellar medium density | Statement: [Local Bubble, gasDensity, much lower than average interstellar medium density]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: gasDensity Context triple: [Local Bubble, gasDensity, much lower than average interstellar medium density]
-
A.
hasMeanDensity
chosen
Indicates that one entity possesses a specified average mass per unit volume (mean density).
-
B.
boilingPoint
Indicates the temperature at which a substance changes from liquid to gas under specified pressure conditions.
-
C.
hasAtmosphere
Indicates that an astronomical body possesses a surrounding layer of gases held by its gravity.
-
D.
hasPopulationDensity
Indicates the number of individuals (e.g., people, organisms) per unit area associated with a given entity or region.
-
E.
massRelativeToEarth
Indicates the comparative amount of mass an entity has relative to the mass of Earth.
- 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_69a4938ce8688190a24bdfef82ba7d21 |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4ac7f98908190883f71049092c7c8 |
completed | March 1, 2026, 9:15 p.m. |
| PD | Predicate disambiguation | batch_69a4aa87504481909618a6815948da6f |
completed | March 1, 2026, 9:07 p.m. |
Created at: March 1, 2026, 7:39 p.m.