Triple
T31650466
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Union Station FlyAway |
E807715
|
entity |
| Predicate | servesRailStation |
P726
|
FINISHED |
| Object | Los Angeles Union Station |
—
|
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: Los Angeles Union Station | Statement: [Union Station FlyAway, servesRailStation, Los Angeles Union Station]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servesRailStation Context triple: [Union Station FlyAway, servesRailStation, Los Angeles Union Station]
-
A.
servedByRailwayTerminus
Indicates that a place or location is provided rail transport services by a specific railway terminus.
-
B.
hasRailStation
chosen
Indicates that one entity possesses, contains, or is served by a rail station.
-
C.
connectsToRailStation
Indicates that one entity has a direct link, route, or access connection to a rail station.
-
D.
servesLocalTrains
Indicates that a station or facility provides service or stops specifically for local (non-express) train routes.
-
E.
railwayTerminalServed
Indicates that a railway terminal is served by, or has service connections with, a particular railway line, route, or operator.
- 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_69f348daf95c81908b4c985b7ddcd0b3 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69fedd5a5f4c8190acce88db56303703 |
completed | May 9, 2026, 7:08 a.m. |
| PD | Predicate disambiguation | batch_69fed910b31c8190ae837163d146738d |
completed | May 9, 2026, 6:49 a.m. |
Created at: April 30, 2026, 10:53 p.m.