Triple
T6695573
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Filchner-Ronne Ice Shelf |
E152740
|
entity |
| Predicate | iceThickness |
P29933
|
FINISHED |
| Object | up to several hundred meters thick |
—
|
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: up to several hundred meters thick | Statement: [Filchner-Ronne Ice Shelf, iceThickness, up to several hundred meters thick]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: iceThickness Context triple: [Filchner-Ronne Ice Shelf, iceThickness, up to several hundred meters thick]
-
A.
typicalIceThickness
chosen
Indicates the usual or characteristic thickness of ice under normal or representative conditions.
-
B.
hasIceSurface
Indicates that an entity possesses or is characterized by a surface composed primarily of ice.
-
C.
iceFeature
Indicates a relationship where a geographic or environmental feature is composed of, covered by, or characterized by ice.
-
D.
iceClass
Indicates a classification relationship specifying the level or category of ice-strengthening or ice-navigation capability assigned to a vessel or structure.
-
E.
hasIcebergs
Indicates that one entity (typically a body of water or region) contains or is characterized by the presence of icebergs.
- 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_69c6880687b08190805278b504d1c92c |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6b5ed99e48190970805225458ce82 |
completed | March 27, 2026, 4:53 p.m. |
| PD | Predicate disambiguation | batch_69c6ad0e1d348190af1762ea1951038e |
completed | March 27, 2026, 4:15 p.m. |
Created at: March 27, 2026, 2:05 p.m.