Triple
T21248958
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | British–Irish Ice Sheet |
E523689
|
entity |
| Predicate | createdLandforms |
P124437
|
FINISHED |
| Object | glacial valleys |
—
|
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: glacial valleys | Statement: [British–Irish Ice Sheet, createdLandforms, glacial valleys]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: createdLandforms Context triple: [British–Irish Ice Sheet, createdLandforms, glacial valleys]
-
A.
createsLandform
chosen
Indicates that one entity brings about the formation or existence of a physical landform in relation to another entity.
-
B.
hasLandform
Indicates that one entity possesses, contains, or is characterized by a particular natural landform.
-
C.
connectsLandform
Indicates a relationship where one landform serves as a physical link or passage between two or more other landforms.
-
D.
geologicalFormation
Indicates that one entity is a geological structure or feature that characterizes or composes the physical makeup of another entity.
-
E.
hasLandformOrigin
Indicates that something originates from, or is formed by, a particular landform.
- 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_69e0b5146c108190adc9adb73e90abff |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e7359c7a648190b4345336ac3be024 |
completed | April 21, 2026, 8:30 a.m. |
| PD | Predicate disambiguation | batch_69e5f61239708190ab7b3c83ae848a0d |
completed | April 20, 2026, 9:46 a.m. |
Created at: April 16, 2026, 3:56 p.m.