Triple
T3672232
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Damascene steel |
E77905
|
entity |
| Predicate | microstructure |
P22287
|
FINISHED |
| Object | carbide banding |
—
|
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: carbide banding | Statement: [Damascene steel, microstructure, carbide banding]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: microstructure Context triple: [Damascene steel, microstructure, carbide banding]
-
A.
crystalStructure
Indicates the specific geometric arrangement of atoms or molecules in a crystalline material.
-
B.
microscopicMacroscopicLink
Indicates a relationship where microscopic-level phenomena or properties are causally or explanatorily connected to macroscopic-level behavior or observations.
-
C.
material
Indicates that one entity is physically composed of, made from, or constructed using the substance or material represented by the other entity.
-
D.
cellStructure
Indicates the structural organization, components, and physical arrangement that make up a cell.
-
E.
internalStructure
chosen
Indicates that one entity is a component, part, or substructure contained within the overall structure of 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_69ad85e083008190b2e1b7085fe500bd |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc42de1bc819090e19dd0805f13a1 |
completed | March 8, 2026, 6:47 p.m. |
| PD | Predicate disambiguation | batch_69adb84a20288190a092e4a1b045fe3f |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:25 p.m.