Triple
T38682419
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Glacier Bay icefield system |
E949022
|
entity |
| Predicate | runoffFeeds |
P162420
|
FINISHED |
| Object | Glacier Bay fjord system |
—
|
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: Glacier Bay fjord system | Statement: [Glacier Bay icefield system, runoffFeeds, Glacier Bay fjord system]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: runoffFeeds Context triple: [Glacier Bay icefield system, runoffFeeds, Glacier Bay fjord system]
-
A.
feedsRiver
Indicates that one water body or source supplies water to and flows into a river.
-
B.
feedsViaAqueduct
Indicates that something supplies or channels a resource (typically water) to another thing through an aqueduct.
-
C.
feedsOn
Indicates that one entity obtains nourishment by consuming another entity as food.
-
D.
feedsOrDrains
chosen
Indicates that one entity supplies resources or energy to another or removes them from it, acting as either a source (feeds) or a sink (drains).
-
E.
feedsAt
Indicates that one entity obtains or consumes food at, from, or using another entity (such as a location, source, or feeding apparatus).
- 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_69f76efe16148190befd5dd59c3dfeaa |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fce545fec881909247a3af821d21ae |
completed | May 7, 2026, 7:17 p.m. |
| PD | Predicate disambiguation | batch_69fce12eaeec81908cf81346b2cef6e0 |
completed | May 7, 2026, 6:59 p.m. |
Created at: May 3, 2026, 4:33 p.m.