Triple
T27337155
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Worthington Glacier |
E689984
|
entity |
| Predicate | distanceFromValdez |
P76164
|
FINISHED |
| Object | approximately 28 miles |
—
|
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: approximately 28 miles | Statement: [Worthington Glacier, distanceFromValdez, approximately 28 miles]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: distanceFromValdez Context triple: [Worthington Glacier, distanceFromValdez, approximately 28 miles]
-
A.
distanceToValdez
chosen
Indicates the measured distance between a given entity or location and Valdez.
-
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.
approximateDistanceFromAnchorage
Indicates the estimated spatial distance between a given entity and Anchorage, rather than an exact measured value.
-
E.
distanceToTalkeetnaInMiles
Indicates the numerical distance, measured in miles, from a given entity or location to Talkeetna.
- 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_69ef355e5b388190a8fc1eba9b4a6656 |
completed | April 27, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69ff3fb2318c81908a46c2f513608935 |
completed | May 9, 2026, 2:07 p.m. |
| PD | Predicate disambiguation | batch_69ff3e96dcc48190819f6204680d84aa |
completed | May 9, 2026, 2:03 p.m. |
Created at: April 27, 2026, 11:41 a.m.