Triple
T12429398
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Port Imperial |
E296985
|
entity |
| Predicate | hasCommercialSpaceType |
P104883
|
FINISHED |
| Object | office space |
—
|
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: office space | Statement: [Port Imperial, hasCommercialSpaceType, office space]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCommercialSpaceType Context triple: [Port Imperial, hasCommercialSpaceType, office space]
-
A.
commercialCrewProvider
Indicates that an entity serves as a commercial provider of crew transportation services, typically to and from space or orbital destinations.
-
B.
commercialLaunchProvider
Indicates that an entity serves as the organization responsible for providing launch services for a commercial space mission or payload.
-
C.
hasSpaceport
Indicates that a location or entity possesses or hosts a spaceport facility for spacecraft operations.
-
D.
spaceAgencyCustomer
Indicates a relationship where one entity is a customer that purchases or contracts services from a space agency.
-
E.
isOnSpacecraftType
Indicates that one entity is currently aboard or assigned to a spacecraft of a specified type.
- F. None of above. chosen
Provenance (4 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_69d6ada0640c81908c061d7fb3d47786 |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d94df948308190ace333230a4a3b38 |
completed | April 10, 2026, 7:22 p.m. |
| PD | Predicate disambiguation | batch_69d94d391c548190996a8c698357f273 |
completed | April 10, 2026, 7:19 p.m. |
| PDg | Predicate description generation | batch_69d94df652cc8190a1d2d685fa87cf98 |
completed | April 10, 2026, 7:22 p.m. |
Created at: April 8, 2026, 9:55 p.m.