Triple
T7803257
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gwangandaegyo |
E180482
|
entity |
| Predicate | lowerDeckFunction |
P68896
|
FINISHED |
| Object | local traffic |
—
|
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: local traffic | Statement: [Gwangandaegyo, lowerDeckFunction, local traffic]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lowerDeckFunction Context triple: [Gwangandaegyo, lowerDeckFunction, local traffic]
-
A.
lowerDeckDirection
Indicates the direction or orientation associated with movement or positioning on the lower deck of a structure or vehicle.
-
B.
hasLowerDeckFunction
chosen
Indicates that an entity serves a specific role or performs a designated function on the lower deck of a structure or vehicle.
-
C.
lowerLocation
Indicates that one entity is located physically below or at a lower vertical position relative to another entity.
-
D.
lowFloor
Indicates that something has a floor positioned close to ground level, allowing easy, step-free access.
-
E.
chamberLower
Indicates that the entity serves as the lower chamber (e.g., house) within a bicameral or multi-chamber legislative or decision-making body.
- 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_69ca827e50cc8190a92a733577184938 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69caf78a6d88819093f83528fe88b182 |
completed | March 30, 2026, 10:22 p.m. |
| PD | Predicate disambiguation | batch_69cae9111b2481909684a2d4aa4831c2 |
completed | March 30, 2026, 9:20 p.m. |
Created at: March 30, 2026, 4:34 p.m.