Triple
T33707798
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mossesundet |
E863647
|
entity |
| Predicate | separatesTownFromIsland |
P18114
|
FINISHED |
| Object | Moss – Jeløya |
—
|
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: Moss – Jeløya | Statement: [Mossesundet, separatesTownFromIsland, Moss – Jeløya]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: separatesTownFromIsland Context triple: [Mossesundet, separatesTownFromIsland, Moss – Jeløya]
-
A.
isSeparatedFromMainlandBy
chosen
Indicates that one land area is divided from the mainland by a specific intervening body or feature, such as water or terrain.
-
B.
separatedFromByLand
Indicates that two entities are divided or kept apart from each other by an intervening landmass.
-
C.
separatedIntoIslandsBy
Indicates that one entity is divided or fragmented into distinct parts or regions by the presence of another entity, forming separate “islands.”
-
D.
separatesSea
Indicates that an agent causes a sea or large body of water to divide into distinct parts or sections.
-
E.
partOfIsland
Indicates that one entity is a portion or component of an island.
- 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_69f3498844608190bb8f9b14908d2510 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6fab770548190a4a27fab2ecc38d7 |
completed | May 3, 2026, 7:35 a.m. |
| PD | Predicate disambiguation | batch_69f6f96dd4c8819093d6a7bd046a9ad5 |
completed | May 3, 2026, 7:29 a.m. |
Created at: May 1, 2026, 1:43 a.m.