Triple
T5028623
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lyon tramway line T3 |
E113238
|
entity |
| Predicate | networkMapColor |
P34402
|
FINISHED |
| Object | light green |
—
|
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: light green | Statement: [Lyon tramway line T3, networkMapColor, light green]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: networkMapColor Context triple: [Lyon tramway line T3, networkMapColor, light green]
-
A.
networkColorOfLine
chosen
Indicates the color assigned to a specific line within a network (such as a transit or communication network).
-
B.
mapColor
Indicates a relationship where a map region or area is assigned or associated with a specific color, typically for visualization or categorization purposes.
-
C.
networkMapName
Indicates the designated name or label assigned to a particular network map within a system or context.
-
D.
circuitColorOnMaps
Indicates that a circuit is represented with a specific color on one or more maps.
-
E.
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.
- 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_69bd443775e48190a646ffbfc4334723 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd738f2cc88190a03eebf19e407411 |
completed | March 20, 2026, 4:19 p.m. |
| PD | Predicate disambiguation | batch_69bd71509e9c8190a60c1d8d04936a12 |
completed | March 20, 2026, 4:09 p.m. |
Created at: March 20, 2026, 1:36 p.m.