Triple
T20191457
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shepherd |
E492986
|
entity |
| Predicate | controlsVehicle |
P30234
|
FINISHED |
| Object | Rescue Corps spaceship |
—
|
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: Rescue Corps spaceship | Statement: [Shepherd, controlsVehicle, Rescue Corps spaceship]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: controlsVehicle Context triple: [Shepherd, controlsVehicle, Rescue Corps spaceship]
-
A.
mainVehicle
Indicates that one vehicle is the primary or most important vehicle associated with a given entity or context.
-
B.
vehicleInteraction
Indicates an interaction or relationship occurring between two or more vehicles, such as influencing each other’s movement, position, or behavior.
-
C.
commandedVehicle
chosen
Indicates that one entity had authoritative control over or issued orders to another entity that is a vehicle.
-
D.
vehicleFunction
Indicates the functional role or primary purpose that a vehicle is designed or used to perform.
-
E.
vehicleUsed
Indicates that a particular vehicle is utilized or employed in performing an action, event, or activity.
- 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_69da6268a034819081cbd9ea5a1c9475 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e66ad593f88190a1e534fed38b3cd7 |
completed | April 20, 2026, 6:05 p.m. |
| PD | Predicate disambiguation | batch_69e55b11124c8190babacf2a0fe2d057 |
completed | April 19, 2026, 10:45 p.m. |
Created at: April 11, 2026, 11:37 p.m.