Triple
T27441534
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Byrd Glacier |
E690947
|
entity |
| Predicate | hasOutletType |
P168083
|
FINISHED |
| Object | outlet glacier |
—
|
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: outlet glacier | Statement: [Byrd Glacier, hasOutletType, outlet glacier]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOutletType Context triple: [Byrd Glacier, hasOutletType, outlet glacier]
-
A.
hasOutlet
Indicates that one entity provides, contains, or is equipped with an outlet or point of access for another entity.
-
B.
hasOutletStructure
Indicates that one entity possesses or is associated with a specific outlet structure through which something (e.g., fluid, energy, or information) is discharged or released.
-
C.
hasOutletWorks
Indicates that an entity has associated works (such as publications, products, or content) that are distributed, presented, or made available through a particular outlet or channel.
-
D.
hasOutletCenterFeature
Indicates that an entity possesses a characteristic, attribute, or component related to an outlet center.
-
E.
hasInlet
Indicates that one entity serves as an inlet or entry point through which another entity receives a flow of material, energy, or fluid.
- 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_69ef5200fa0481908e28508d6e2c149e |
completed | April 27, 2026, 12:09 p.m. |
| NER | Named-entity recognition | batch_69f673633d288190b52ceb9f8a057c44 |
completed | May 2, 2026, 9:57 p.m. |
| PD | Predicate disambiguation | batch_69f66ec3d3d48190ab2f2b71939e572e |
completed | May 2, 2026, 9:38 p.m. |
| PDg | Predicate description generation | batch_69f67256d064819094be04fc1bbbc635 |
completed | May 2, 2026, 9:53 p.m. |
Created at: April 27, 2026, 12:45 p.m.