Triple
T29154526
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Edmonds–Kingston route |
E738999
|
entity |
| Predicate | peninsulaServed |
P89729
|
FINISHED |
| Object | Kitsap Peninsula |
—
|
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: Kitsap Peninsula | Statement: [Edmonds–Kingston route, peninsulaServed, Kitsap Peninsula]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: peninsulaServed Context triple: [Edmonds–Kingston route, peninsulaServed, Kitsap Peninsula]
-
A.
containsPeninsula
Indicates that one geographic region fully or partially includes a landform that is a peninsula within its boundaries.
-
B.
islandServed
Indicates that a particular island is provided with service or coverage (such as transportation, utilities, or infrastructure) by a specified entity.
-
C.
endpointOnPeninsula
chosen
Indicates that one endpoint of an object, path, or feature lies on or within the bounds of a peninsula.
-
D.
peninsulaBetween
Indicates that one landmass forms a peninsula situated between two other geographic entities, separating or partially separating them.
-
E.
isPeninsula
Indicates that a landform is a peninsula, meaning it is surrounded by water on most sides but connected to a larger landmass.
- 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_69f07cb46f148190874eb8576a447567 |
completed | April 28, 2026, 9:24 a.m. |
| NER | Named-entity recognition | batch_69f662a87a6c8190b623bacb42af0097 |
completed | May 2, 2026, 8:46 p.m. |
| PD | Predicate disambiguation | batch_69f65c2376a08190be5215171e908e69 |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 28, 2026, 11:44 a.m.