Triple
T18127203
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | EAST |
E433906
|
entity |
| Predicate | plasmaFacingMaterial |
P103422
|
FINISHED |
| Object | tungsten divertor components |
—
|
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: tungsten divertor components | Statement: [EAST, plasmaFacingMaterial, tungsten divertor components]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: plasmaFacingMaterial Context triple: [EAST, plasmaFacingMaterial, tungsten divertor components]
-
A.
primaryTargetMaterial
Indicates the material that serves as the main or principal target in a given process, action, or interaction.
-
B.
frontMaterial
chosen
Indicates that one entity is the material that forms the front surface or front-facing part of another entity.
-
C.
featuresMaterialType
Indicates that an entity is characterized by or incorporates a specific type of material.
-
D.
wallMaterial
Indicates that one entity is the material from which a wall or walls of another entity are constructed.
-
E.
fuelCladding
Indicates a relationship where a material or component serves as the cladding (protective outer layer) for nuclear fuel.
- 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_69d8b909e8cc81908df4cc2b8ea6d11f |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4ddef4cd88190b16ef0d6ed3968c6 |
completed | April 19, 2026, 1:51 p.m. |
| PD | Predicate disambiguation | batch_69e43313ca788190baa224269e71de49 |
completed | April 19, 2026, 1:42 a.m. |
Created at: April 10, 2026, 10:29 a.m.