Triple
T4393796
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Washington/Wells |
E99430
|
entity |
| Predicate | mapColorPurpleLine |
P55829
|
FINISHED |
| Object | purple |
—
|
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: purple | Statement: [Washington/Wells, mapColorPurpleLine, purple]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mapColorPurpleLine Context triple: [Washington/Wells, mapColorPurpleLine, purple]
-
A.
mapColorBlueLine
Indicates that a map is rendered or highlighted using a blue-colored line to represent a particular feature or path.
-
B.
mapColorLine
Indicates a relationship where a specific color is assigned to or associated with a particular line (such as a route, path, or boundary) on a map.
-
C.
mapColorGreenLine
Indicates that an entity is represented or highlighted with a green-colored line on a map.
-
D.
mapColorYellowLine
Indicates that a map feature is represented or highlighted using a yellow line.
-
E.
mapColorOrangeLine
Indicates that an entity is associated with, represented by, or rendered using the color of the orange line on a map.
- F. None of above. chosen
Provenance (4 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_69b345506b408190b0e3dee616738a7d |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b352a8862481909dc67abf42be6928 |
completed | March 12, 2026, 11:56 p.m. |
| PD | Predicate disambiguation | batch_69b34f597998819092477efdedb51427 |
completed | March 12, 2026, 11:42 p.m. |
| PDg | Predicate description generation | batch_69b34ff654308190b9717526120d80d3 |
completed | March 12, 2026, 11:44 p.m. |
Created at: March 12, 2026, 11:19 p.m.