Triple
T11360090
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | dye-sensitized solar cell |
E269062
|
entity |
| Predicate | typicallyUsesSemiconductor |
P64160
|
FINISHED |
| Object | titanium dioxide |
—
|
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: titanium dioxide | Statement: [dye-sensitized solar cell, typicallyUsesSemiconductor, titanium dioxide]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicallyUsesSemiconductor Context triple: [dye-sensitized solar cell, typicallyUsesSemiconductor, titanium dioxide]
-
A.
usedSemiconductorType
chosen
Indicates that one entity employs or incorporates a specific type of semiconductor in its design, construction, or operation.
-
B.
hardwareUsedBy
Indicates that a piece of hardware is utilized or operated by a particular entity (such as a person, system, or organization).
-
C.
mainlyUses
Indicates that one entity primarily relies on, employs, or utilizes another entity as its main tool, method, resource, or medium.
-
D.
technologyUsedIn
Indicates that a particular technology is employed or applied within a specific process, product, context, or domain.
-
E.
usesSoC
Indicates that one entity incorporates or relies on a particular system-on-chip (SoC) as a core hardware component for its operation.
- 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_69d6aacbe18081909e5fadb50082dd96 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d800160a1c81909d115bf89fe54a49 |
completed | April 9, 2026, 7:37 p.m. |
| PD | Predicate disambiguation | batch_69d7e7022d508190996f9be0847c2b41 |
completed | April 9, 2026, 5:50 p.m. |
Created at: April 8, 2026, 9:33 p.m.