Triple
T2946563
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Furtwängler Glacier |
E79515
|
entity |
| Predicate | hasTemporalCharacteristic |
P42651
|
FINISHED |
| Object | formed during late Holocene |
—
|
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: formed during late Holocene | Statement: [Furtwängler Glacier, hasTemporalCharacteristic, formed during late Holocene]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTemporalCharacteristic Context triple: [Furtwängler Glacier, hasTemporalCharacteristic, formed during late Holocene]
-
A.
hasTemporalLocation
Indicates that something occurs, exists, or is valid during a specific time or time interval.
-
B.
temporalAspect
Indicates the time-related characteristics or phase (such as duration, frequency, or temporal status) associated with an event or relationship.
-
C.
timeCharacteristic
chosen
Indicates a relationship where one entity specifies a temporal property, feature, or constraint that characterizes another entity or event.
-
D.
temporalRelation
Indicates a relationship that specifies how two events or states are positioned relative to each other in time (e.g., before, after, or overlapping).
-
E.
hasTimeDepth
Indicates that something possesses or spans a measurable extent of time, such as duration, historical depth, or temporal layering.
- 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_69ad8b1089588190b74d9e2505e45762 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad98b3f86c819094526c2af611bfb5 |
completed | March 8, 2026, 3:41 p.m. |
| PD | Predicate disambiguation | batch_69ad960a70ac8190816b5ae3e8631031 |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 2:56 p.m.