Triple
T22989296
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sohae Satellite Launching Station |
E572001
|
entity |
| Predicate | hasRunwayOrRailAccess |
P124024
|
FINISHED |
| Object | rail access |
—
|
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: rail access | Statement: [Sohae Satellite Launching Station, hasRunwayOrRailAccess, rail access]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRunwayOrRailAccess Context triple: [Sohae Satellite Launching Station, hasRunwayOrRailAccess, rail access]
-
A.
hasRunwayAccessVia
Indicates that an entity has access to a runway by means of a specified connecting route, facility, or intermediary.
-
B.
hasRunwayAccessTo
Indicates that one location or facility is directly connected to another via a usable runway, allowing aircraft to move between them without leaving runway infrastructure.
-
C.
hasRunwayType
Indicates that an airport or airfield has a runway of a specified type or surface classification.
-
D.
hasRunwayPresence
Indicates that an entity maintains a physical runway or landing strip suitable for aircraft operations.
-
E.
hasRailOrRoadAccess
chosen
Indicates that an entity is connected to or reachable by either a railway network, a road network, or both.
- 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_69e245b535808190adef8a9df3c584db |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f182ea55cc8190b64b722ce8c45b53 |
completed | April 29, 2026, 4:02 a.m. |
| PD | Predicate disambiguation | batch_69ef3b974e7c8190b8be11dbb4518693 |
completed | April 27, 2026, 10:33 a.m. |
Created at: April 17, 2026, 3:49 p.m.