Triple
T25407095
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Orust |
E636588
|
entity |
| Predicate | rankInSizeInSweden |
P163833
|
FINISHED |
| Object | third-largest island excluding Gotland and Öland |
—
|
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: third-largest island excluding Gotland and Öland | Statement: [Orust, rankInSizeInSweden, third-largest island excluding Gotland and Öland]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rankInSizeInSweden Context triple: [Orust, rankInSizeInSweden, third-largest island excluding Gotland and Öland]
-
A.
cityRankInSwedenBySize
Indicates the relative position of a city in Sweden when cities are ordered by their size (typically population or area).
-
B.
rankInSwedenByHeight
Indicates the position an entity holds in an ordered list of entities in Sweden when sorted by their height.
-
C.
lengthInSweden
Indicates that something has a specified length measured within the context or territory of Sweden.
-
D.
strengthSweden
Indicates the level or degree of strength associated with Sweden in a given context.
-
E.
chartPositionSweden
Indicates the position or ranking something holds on a music or sales chart specifically in Sweden.
- F. None of above. chosen
Provenance (4 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_69e75db361d881908d8701c856da6413 |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f6416fbf4081909b0913c337927fc4 |
completed | May 2, 2026, 6:24 p.m. |
| PD | Predicate disambiguation | batch_69f63c6456608190b94e7c2e2c2a4824 |
completed | May 2, 2026, 6:03 p.m. |
| PDg | Predicate description generation | batch_69f63fd4f7448190930c723ba7cfce62 |
completed | May 2, 2026, 6:17 p.m. |
Created at: April 21, 2026, 1:52 p.m.