Triple
T6391497
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Upsala Glacier |
E143836
|
entity |
| Predicate | hasRetreatConsequence |
P812
|
FINISHED |
| Object | formation of proglacial lakes |
—
|
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: formation of proglacial lakes | Statement: [Upsala Glacier, hasRetreatConsequence, formation of proglacial lakes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRetreatConsequence Context triple: [Upsala Glacier, hasRetreatConsequence, formation of proglacial lakes]
-
A.
hasRetreatExposing
Indicates that an entity has a retreat or fallback position that, when used, exposes it or makes it vulnerable in some way.
-
B.
isRetreating
Indicates that an entity is moving away from a location, opponent, or situation, typically to withdraw or escape from engagement.
-
C.
hasConsequence
chosen
Indicates that one event, action, or condition leads to or results in another as its outcome or effect.
-
D.
hasRetreatedSince
Indicates that an entity has withdrawn or moved back from a position or engagement at some point after a specified reference time or event.
-
E.
retreatCause
Indicates that one event, condition, or factor serves as the reason or trigger for a retreat by an entity.
- 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_69c008db906c819096f3597d55d95432 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c0687db4b881909dd84d5a947cc3e3 |
completed | March 22, 2026, 10:09 p.m. |
| PD | Predicate disambiguation | batch_69c060f25c088190b433f78553ff1d84 |
completed | March 22, 2026, 9:36 p.m. |
Created at: March 22, 2026, 4:34 p.m.