Triple
T6743623
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Green Line (MARTA) |
E154151
|
entity |
| Predicate | systemColorCoding |
P62473
|
FINISHED |
| Object | color-coded line |
—
|
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: color-coded line | Statement: [Green Line (MARTA), systemColorCoding, color-coded line]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: systemColorCoding Context triple: [Green Line (MARTA), systemColorCoding, color-coded line]
-
A.
colorSystem
chosen
Indicates that one entity is a system or scheme used to define, organize, or represent the colors of another entity.
-
B.
colorDisplay
Indicates that one entity presents, shows, or renders the color associated with another entity.
-
C.
insigniaColorContext
Indicates the contextual circumstances or conditions under which a particular insignia color is used or holds its specific meaning.
-
D.
hasColourScheme
Indicates that an entity is associated with a particular set or pattern of colors used in its design or appearance.
-
E.
serialNumberColor
Indicates a relationship where a specific serial number is associated with a particular color.
- 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_69c6880d84d8819095d19de2295f26ac |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d1b3b1448190a94b4b64f01af14a |
completed | March 27, 2026, 6:51 p.m. |
| PD | Predicate disambiguation | batch_69c6d09067a0819087ed6c820f4699f8 |
completed | March 27, 2026, 6:46 p.m. |
Created at: March 27, 2026, 2:10 p.m.