Triple
T18827148
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gerry Cheevers |
E460416
|
entity |
| Predicate | maskDesign |
P45253
|
FINISHED |
| Object | white mask with painted black stitches |
—
|
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: white mask with painted black stitches | Statement: [Gerry Cheevers, maskDesign, white mask with painted black stitches]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maskDesign Context triple: [Gerry Cheevers, maskDesign, white mask with painted black stitches]
-
A.
maskDesigner
Indicates that one entity is the designer or creator of a particular mask associated with another entity.
-
B.
maskColor
Indicates the color attribute associated with a mask.
-
C.
maskPattern
Indicates a relationship where one entity serves as a masking template or pattern that determines which parts or aspects of another entity are revealed, hidden, or transformed.
-
D.
mask
Indicates that one entity covers, conceals, or obscures another entity, typically to hide its identity, appearance, or specific features.
-
E.
frontDesign
chosen
Indicates that one entity serves as the primary or visible front-facing design or appearance 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_69d8dcf94c288190a06dea029ae4b223 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5a6bfa4a88190b17d3118121414be |
completed | April 20, 2026, 4:08 a.m. |
| PD | Predicate disambiguation | batch_69e48d1b10ec8190985c6fb5766ff981 |
completed | April 19, 2026, 8:06 a.m. |
Created at: April 10, 2026, 11:56 a.m.