Triple
T15818503
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Washington Harbor |
E383539
|
entity |
| Predicate | locatedOnSideOfIsleRoyale |
P44066
|
FINISHED |
| Object | southwest side of Isle Royale |
—
|
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: southwest side of Isle Royale | Statement: [Washington Harbor, locatedOnSideOfIsleRoyale, southwest side of Isle Royale]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locatedOnSideOfIsleRoyale Context triple: [Washington Harbor, locatedOnSideOfIsleRoyale, southwest side of Isle Royale]
-
A.
isOnSideOfIsland
chosen
Indicates that one entity is located on a particular side or shore of an island relative to some reference or division.
-
B.
isOnIslandInLake
Indicates that one entity is located on an island that is situated within a lake associated with another entity.
-
C.
partOfIsland
Indicates that one entity is a portion or component of an island.
-
D.
locatedOnSideOfAtoll
Indicates that one entity is situated along or on a particular side of an atoll.
-
E.
meetsInIsland
Indicates that two or more entities meet with each other at a location that is 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_69d86da2858c819090cc8481e7207b6e |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e0c4a552008190863343c9d41ebf3f |
completed | April 16, 2026, 11:14 a.m. |
| PD | Predicate disambiguation | batch_69e0053b847c8190945726c3ddac21cc |
completed | April 15, 2026, 9:38 p.m. |
Created at: April 10, 2026, 4:49 a.m.