Triple
T29530634
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Germany–Scandinavia |
E749190
|
entity |
| Predicate | hasKeyPortInSweden |
P104217
|
FINISHED |
| Object | Trelleborg |
—
|
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: Trelleborg | Statement: [Germany–Scandinavia, hasKeyPortInSweden, Trelleborg]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasKeyPortInSweden Context triple: [Germany–Scandinavia, hasKeyPortInSweden, Trelleborg]
-
A.
hasNobilityEstateInSweden
Indicates that a person or entity possesses a noble estate or noble status recognized in Sweden.
-
B.
hasKeyPort
chosen
Indicates that an entity possesses or is associated with a primary or main port used for connection, access, or communication.
-
C.
statusInSweden
Indicates the legal, social, or official standing or condition that an entity holds within the context of Sweden.
-
D.
isBalticPortRegion
Indicates that a region functions as a port area located on or directly connected to the Baltic Sea.
-
E.
nearCityOnSwedishSide
Indicates that one entity is located close to a specified city that lies on the Swedish side of a border or boundary.
- 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_69f0bd46d99c81908ba9d01cc1dbef7d |
completed | April 28, 2026, 1:59 p.m. |
| NER | Named-entity recognition | batch_69f71996e1a48190ac59a1d66d7c44e8 |
completed | May 3, 2026, 9:47 a.m. |
| PD | Predicate disambiguation | batch_69f71820c6c88190ab38b4fa626d22cc |
completed | May 3, 2026, 9:40 a.m. |
Created at: April 28, 2026, 4:52 p.m.