Triple
T7916868
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gustavus, Alaska |
E183848
|
entity |
| Predicate | distanceTo Juneau (approximate, by air) |
P79758
|
FINISHED |
| Object | about 48 miles west |
—
|
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: about 48 miles west | Statement: [Gustavus, Alaska, distanceTo Juneau (approximate, by air), about 48 miles west]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: distanceTo Juneau (approximate, by air) Context triple: [Gustavus, Alaska, distanceTo Juneau (approximate, by air), about 48 miles west]
-
A.
approximateDrivingTimeFromJuneau
Indicates the estimated amount of time it takes to drive from Juneau to another specified location.
-
B.
distanceFromAnchorage
Indicates the measured distance between a given location or object and Anchorage.
-
C.
distanceFromFairbanks
Indicates the spatial distance between a given location or entity and the city of Fairbanks.
-
D.
distanceFromTacoma (miles)
Indicates the physical distance, measured in miles, between an entity’s location and the city of Tacoma.
-
E.
distanceToSeattle
Indicates the measured or calculated distance between a given entity’s location and the city of Seattle.
- 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_69ca828efbe48190bd48482650182e79 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb3a8e8b388190b5544eb5b8159e07 |
completed | March 31, 2026, 3:07 a.m. |
| PD | Predicate disambiguation | batch_69cae9316e98819080be7bf1a6ff92f1 |
completed | March 30, 2026, 9:20 p.m. |
| PDg | Predicate description generation | batch_69caf7882b048190baa333af9f698590 |
completed | March 30, 2026, 10:22 p.m. |
Created at: March 30, 2026, 5:05 p.m.