Triple
T22400704
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Perseus Cluster |
E553749
|
entity |
| Predicate | temperatureOfIntraclusterGas |
P147672
|
FINISHED |
| Object | tens of millions of kelvin |
—
|
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: tens of millions of kelvin | Statement: [Perseus Cluster, temperatureOfIntraclusterGas, tens of millions of kelvin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: temperatureOfIntraclusterGas Context triple: [Perseus Cluster, temperatureOfIntraclusterGas, tens of millions of kelvin]
-
A.
temperatureOfIntraclusterMedium
Indicates the temperature value associated with the intracluster medium in a galaxy cluster.
-
B.
containsHotGas
Indicates that one entity encloses or holds within it a quantity or region of hot gas.
-
C.
hasTemperatureOfICM
chosen
Indicates that an entity (e.g., a medium or environment) possesses a specific temperature value associated with the intracluster medium (ICM).
-
D.
hostGalaxyClusterCenter
Indicates that the subject galaxy cluster serves as the central or primary cluster hosting the object galaxy or system.
-
E.
hostGalaxyClusterMembership
Indicates that an astronomical object’s host galaxy is a member of a particular galaxy cluster.
- 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_69e11e4da7048190b4387d422a9a0de5 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f158b39c908190a735aa860d733869 |
completed | April 29, 2026, 1:02 a.m. |
| PD | Predicate disambiguation | batch_69e8989495bc81909d2699fce5992e28 |
completed | April 22, 2026, 9:44 a.m. |
Created at: April 16, 2026, 8:46 p.m.