Triple
T9982678
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hermann Köhl |
E196490
|
entity |
| Predicate | directionOfTransatlanticFlight |
P73274
|
FINISHED |
| Object | east-to-west |
—
|
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: east-to-west | Statement: [Hermann Köhl, directionOfTransatlanticFlight, east-to-west]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: directionOfTransatlanticFlight Context triple: [Hermann Köhl, directionOfTransatlanticFlight, east-to-west]
-
A.
flightRoute
Indicates a path or sequence of locations that a particular flight travels between, typically from its origin to its destination (and possibly via intermediate stops).
-
B.
destinationOfFlight
Indicates the location or place to which a given flight is traveling or scheduled to arrive.
-
C.
borderDirectionRelativeToNewYork
Indicates the compass direction in which an entity’s border lies relative to the location of New York.
-
D.
travelsDirection
chosen
Indicates that an entity moves or is transported in a specified directional heading or orientation.
-
E.
performedFlightTo
Indicates that an entity (such as an aircraft or airline) carried out a flight whose destination was a specified location.
- 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_69ca82efbce081908179b4b9c65096eb |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdb8bca41081909c04fb77603403b9 |
completed | April 2, 2026, 12:30 a.m. |
| PD | Predicate disambiguation | batch_69cd1d9daa808190b413a1b9a1e929e2 |
completed | April 1, 2026, 1:29 p.m. |
Created at: March 30, 2026, 8:49 p.m.