Triple
T4508607
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sky Red Line |
E101993
|
entity |
| Predicate | exhaust |
P32744
|
FINISHED |
| Object | dual exhaust outlets |
—
|
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: dual exhaust outlets | Statement: [Sky Red Line, exhaust, dual exhaust outlets]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: exhaust Context triple: [Sky Red Line, exhaust, dual exhaust outlets]
-
A.
exhaustType
chosen
Indicates the specific kind or configuration of exhaust system associated with an entity.
-
B.
expel
Indicates forcing an entity to leave or be removed from a place, group, or situation, typically as a punishment or consequence.
-
C.
emissionsControl
Indicates a relationship where one entity regulates, limits, or manages the release of emissions produced by another entity or process.
-
D.
engine
Indicates a relationship where something functions as, contains, or is driven by an engine as its source of mechanical power or propulsion.
-
E.
emitted
Indicates that one entity has released, discharged, or sent out another entity, such as energy, particles, signals, or substances, into its surroundings.
- 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_69bd43d6251c81909deecce3e6e9d69c |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd570f9b1c8190b52ace855dbf6641 |
completed | March 20, 2026, 2:17 p.m. |
| PD | Predicate disambiguation | batch_69bd5218afb4819087c99e0a1f22e137 |
completed | March 20, 2026, 1:56 p.m. |
Created at: March 20, 2026, 1:01 p.m.