Triple
T14188708
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Norris Glacier |
E351650
|
entity |
| Predicate | hasMassBalance |
P113141
|
FINISHED |
| Object | climate-sensitive |
—
|
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: climate-sensitive | Statement: [Norris Glacier, hasMassBalance, climate-sensitive]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMassBalance Context triple: [Norris Glacier, hasMassBalance, climate-sensitive]
-
A.
massBalance
Indicates that the total mass entering a system equals the total mass leaving or accumulating within it, reflecting conservation of mass.
-
B.
typeOfMassBalance
Indicates a relationship where one entity specifies the particular kind or category of mass balance associated with another entity.
-
C.
hasMassScale
Indicates that an entity is associated with a particular mass measurement scale or system used to quantify its mass.
-
D.
hasMasses
Indicates that one entity possesses or is associated with one or more masses (quantities of matter).
-
E.
hasWaterBalance
Indicates that an entity maintains or exhibits a particular state or condition of water balance, such as hydration level or equilibrium between water intake and loss.
- 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_69d827894ac0819097803e57f3227b23 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de61de509881908967ef5031f2a8d9 |
completed | April 14, 2026, 3:48 p.m. |
| PD | Predicate disambiguation | batch_69de05baed64819096590e5618a3a8ed |
completed | April 14, 2026, 9:15 a.m. |
| PDg | Predicate description generation | batch_69de239a02e881909b0e2679487e4ab2 |
completed | April 14, 2026, 11:23 a.m. |
Created at: April 10, 2026, 1:03 a.m.