Triple
T28189134
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Theia |
E716252
|
entity |
| Predicate | supportsPackaging |
P91061
|
FINISHED |
| Object | Electron |
—
|
NE NERFINISHED |
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: Electron | Statement: [Theia, supportsPackaging, Electron]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsPackaging Context triple: [Theia, supportsPackaging, Electron]
-
A.
supportsPackagingModel
chosen
Indicates that one entity provides compatibility with or functionality for a particular packaging model used by another entity.
-
B.
supportsRecordPacking
Indicates that one entity is capable of handling or enabling the packing of records into a more compact or bundled form for another entity or process.
-
C.
commonPackagingFeatures
Indicates that two or more products share the same or very similar packaging characteristics or design elements.
-
D.
packaging
Indicates that one entity serves as the container, wrapper, or enclosing material used to package another entity.
-
E.
supportsPackageShipments
Indicates that one entity provides the capability or service needed to handle and transport package shipments for 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_69efd6b612f48190a72012b520afbd10 |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_6a0075be7f54819081ab12bc1dab53bb |
completed | May 10, 2026, 12:10 p.m. |
| PD | Predicate disambiguation | batch_6a0073a19030819098c23faa3adcb96e |
completed | May 10, 2026, 12:01 p.m. |
Created at: April 27, 2026, 10:24 p.m.