Triple
T14385545
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | U.S. Marine Corps text markings |
E356712
|
entity |
| Predicate | typicalFontStyle |
P57048
|
FINISHED |
| Object | block lettering |
—
|
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: block lettering | Statement: [U.S. Marine Corps text markings, typicalFontStyle, block lettering]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalFontStyle Context triple: [U.S. Marine Corps text markings, typicalFontStyle, block lettering]
-
A.
typicalVisualStyle
Indicates the characteristic or commonly observed visual appearance or aesthetic style associated with an entity.
-
B.
styleFamily
Indicates that one style is grouped within the same stylistic family or category as another style.
-
C.
characterStyle
chosen
Indicates how a character is visually or typographically presented, such as its font, weight, size, or decorative attributes.
-
D.
textualFamily
Indicates that two or more texts are related through a shared origin, tradition, or lineage, forming a recognizable textual group or family.
-
E.
typicalSymbol
Indicates that something serves as a characteristic or commonly recognized symbol representing something else.
- 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_69d827927c988190ad98bb0360981783 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de9025cff881908c08224d90d9f750 |
completed | April 14, 2026, 7:06 p.m. |
| PD | Predicate disambiguation | batch_69de2aa024c48190805df6a9d63deb10 |
completed | April 14, 2026, 11:53 a.m. |
Created at: April 10, 2026, 1:16 a.m.