Triple
T33840251
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Soft Capture and Rendezvous System |
E867339
|
entity |
| Predicate | installationVehicle |
P128874
|
FINISHED |
| Object | Space Shuttle Atlantis |
—
|
NE NERFINISHED |
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: Space Shuttle Atlantis | Statement: [Soft Capture and Rendezvous System, installationVehicle, Space Shuttle Atlantis]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: installationVehicle Context triple: [Soft Capture and Rendezvous System, installationVehicle, Space Shuttle Atlantis]
-
A.
mountVehicle
Indicates initiating the action of getting onto or into a vehicle in order to use or ride it.
-
B.
intendedForVehicle
chosen
Indicates that something is designed, meant, or suitable to be used with or by a particular vehicle.
-
C.
intendedVehicle
Indicates that one entity is the vehicle that another entity plans or is meant to use.
-
D.
supportsVehicle
Indicates that one entity provides the necessary strength, stability, or structure to bear the weight of a vehicle.
-
E.
basedOnVehicle
Indicates that one entity is derived from, modeled after, or otherwise conceptually or functionally based on a particular vehicle.
- 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_69f34992ad40819087760ed939bd2a7a |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f7004e55988190a2d35d4a95a34610 |
completed | May 3, 2026, 7:59 a.m. |
| PD | Predicate disambiguation | batch_69f6fc59518081908b0275f47721d561 |
completed | May 3, 2026, 7:42 a.m. |
Created at: May 1, 2026, 1:47 a.m.