Triple
T16303336
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Russian Service Module Zvezda aft port |
E395843
|
entity |
| Predicate | spaceStationElementOf |
P111363
|
FINISHED |
| Object | ISS long-term configuration |
—
|
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: ISS long-term configuration | Statement: [Russian Service Module Zvezda aft port, spaceStationElementOf, ISS long-term configuration]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: spaceStationElementOf Context triple: [Russian Service Module Zvezda aft port, spaceStationElementOf, ISS long-term configuration]
-
A.
spaceStationModuleOf
chosen
Indicates that one entity is a module or component that forms part of a particular space station.
-
B.
spaceStationServed
Indicates that a particular space station is or was serviced, supplied, or supported by a specific mission, vehicle, or service entity.
-
C.
spaceStationType
Indicates the specific functional or structural category to which a space station belongs (e.g., research, military, commercial).
-
D.
spaceStationName
Indicates that an entity has the specified name of a space station.
-
E.
spaceStationExpedition
Indicates a mission or expedition undertaken to travel to, work on, or return from a space station.
- 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_69d87f23bb088190a16fbb91a1957ea5 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e25e35157481909e5604b7dae7a2a2 |
completed | April 17, 2026, 4:22 p.m. |
| PD | Predicate disambiguation | batch_69e219fa5508819097e9d383348bf174 |
completed | April 17, 2026, 11:31 a.m. |
Created at: April 10, 2026, 5:06 a.m.