Triple
T2634518
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Johnston typeface |
E59711
|
entity |
| Predicate | colorUsageContext |
P7182
|
FINISHED |
| Object | often set in blue on Underground signage |
—
|
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: often set in blue on Underground signage | Statement: [Johnston typeface, colorUsageContext, often set in blue on Underground signage]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: colorUsageContext Context triple: [Johnston typeface, colorUsageContext, often set in blue on Underground signage]
-
A.
hasTypicalUseContext
Indicates that something is commonly or characteristically used within a particular situation, setting, or context.
-
B.
colorReferenceExplains
Indicates that one color reference serves to clarify, define, or provide explanatory information about another color-related element or notation.
-
C.
typicalAppearanceContext
Indicates the usual situation, setting, or context in which an entity most commonly appears or is typically encountered.
-
D.
scopeOfUse
Indicates the range, context, or conditions under which something is intended, allowed, or applicable to be used.
-
E.
colorOftenUsed
chosen
Indicates that a particular color is frequently used or commonly applied in relation to something.
- 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_69ab4ac8596c8190b34997e73d9e991c |
completed | March 6, 2026, 9:44 p.m. |
| NER | Named-entity recognition | batch_69abd8e085b0819089db4103c0d8cd9b |
completed | March 7, 2026, 7:50 a.m. |
| PD | Predicate disambiguation | batch_69abd812849881908f956845a80e0205 |
completed | March 7, 2026, 7:47 a.m. |
Created at: March 6, 2026, 9:50 p.m.