Triple
T15898765
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thorne Bay |
E385529
|
entity |
| Predicate | isRoadConnectedWithinIsland |
P120973
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [Thorne Bay, isRoadConnectedWithinIsland, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isRoadConnectedWithinIsland Context triple: [Thorne Bay, isRoadConnectedWithinIsland, true]
-
A.
isOnIslandRoute
Indicates that something (such as a path, trip, or connection) follows a route that involves traveling to, from, or around an island.
-
B.
isRemoteByRoad
Indicates that one location is difficult or time-consuming to reach from another when traveling by road.
-
C.
hasIslandBetweenBranches
Indicates that there is an island located in the area where the branches of something (such as a river or structure) diverge or lie between them.
-
D.
isScenicConnectorBetween
Indicates that something serves as a visually appealing route or link connecting two locations or entities.
-
E.
connectedIsland
Indicates that two islands are linked by a direct or indirect path, such that travel or communication between them is possible within the same connected group.
- 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_69d86da5b800819083a31be937d738b0 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e17d4d08f481909f38b75e3f42d9ab |
completed | April 17, 2026, 12:22 a.m. |
| PD | Predicate disambiguation | batch_69e142ca3b208190946c3aa4c1e6087c |
completed | April 16, 2026, 8:12 p.m. |
| PDg | Predicate description generation | batch_69e17d48cc9c8190b03fd07ae2e9dfd8 |
completed | April 17, 2026, 12:22 a.m. |
Created at: April 10, 2026, 4:51 a.m.