Triple
T24217990
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Viðey Island |
E601358
|
entity |
| Predicate | ferryDeparturePoint |
P1521
|
FINISHED |
| Object | Skarfabakki harbour |
—
|
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: Skarfabakki harbour | Statement: [Viðey Island, ferryDeparturePoint, Skarfabakki harbour]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ferryDeparturePoint Context triple: [Viðey Island, ferryDeparturePoint, Skarfabakki harbour]
-
A.
ferryTerminalName
Indicates the name assigned to a ferry terminal involved in the relationship or action.
-
B.
hasNearbyFerryPort
Indicates that one location is situated close enough to another location that serves as a ferry port to be considered nearby.
-
C.
placeOfDeparture
chosen
Indicates the location from which an entity, such as a person or vehicle, begins its journey or movement.
-
D.
hasFerryPort
Indicates that a place serves as a location where ferries regularly dock to load and unload passengers or cargo.
-
E.
eraOfMajorUseAsFerryTerminal
Indicates the time period during which a location was primarily used as a ferry terminal.
- 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_69e29537ca548190b94a37ebe1977caf |
completed | April 17, 2026, 8:16 p.m. |
| NER | Named-entity recognition | batch_69f2820a80ec8190bd11f08f7733843d |
completed | April 29, 2026, 10:11 p.m. |
| PD | Predicate disambiguation | batch_69f1c448abec8190b87cbf9ed419a309 |
completed | April 29, 2026, 8:41 a.m. |
Created at: April 17, 2026, 11:58 p.m.