Triple
T17498642
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Skagway Airport |
E426137
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Skagway |
—
|
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: Skagway | Statement: [Skagway Airport, locatedIn, Skagway]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Skagway Context triple: [Skagway Airport, locatedIn, Skagway]
-
A.
Skagway
chosen
Skagway is a historic Alaskan town known as a gateway to the Klondike Gold Rush region and a popular cruise ship stop in the Inside Passage.
-
B.
Ketchikan
Ketchikan is a coastal city in southeastern Alaska known for its rich Native Alaskan culture, historic downtown, and status as a major cruise ship and fishing port.
-
C.
Petersburg, Alaska
Petersburg, Alaska is a small fishing town in Southeast Alaska known for its strong Norwegian heritage and thriving commercial fishing industry.
-
D.
Dyea, Alaska
Dyea, Alaska is a historic ghost town and former boomtown near Skagway that served as a major gateway to the Klondike Gold Rush via the Chilkoot Trail.
-
E.
Yakutat
Yakutat is a small coastal city in southeastern Alaska known for its remote location, fishing industry, and access to the Gulf of Alaska’s rugged natural landscapes.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d889dccf7481909264a1844a2e9100 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e4521028048190aa7c4023a72a12f4 |
completed | April 19, 2026, 3:54 a.m. |
Created at: April 10, 2026, 5:48 a.m.