Triple
T6695583
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Filchner-Ronne Ice Shelf |
E152740
|
entity |
| Predicate | hasIceFront |
P71514
|
FINISHED |
| Object | Filchner Ice Shelf front in the eastern sector |
—
|
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: Filchner Ice Shelf front in the eastern sector | Statement: [Filchner-Ronne Ice Shelf, hasIceFront, Filchner Ice Shelf front in the eastern sector]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasIceFront Context triple: [Filchner-Ronne Ice Shelf, hasIceFront, Filchner Ice Shelf front in the eastern sector]
-
A.
hasIceSurface
Indicates that an entity possesses or is characterized by a surface composed primarily of ice.
-
B.
hasIceSheet
Indicates that one entity possesses, is covered by, or contains an ice sheet.
-
C.
hasSeaIce
Indicates that one entity possesses, contains, or is covered by sea ice in relation to another context or location.
-
D.
hasIcebergs
Indicates that one entity (typically a body of water or region) contains or is characterized by the presence of icebergs.
-
E.
hasIceShelf
Indicates that a glacier, ice sheet, or coastline possesses an attached floating extension of ice known as an ice shelf.
- 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_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. |
| PDg | Predicate description generation | batch_69c6b5ec6f248190b4fa15fd56dcc01a |
completed | March 27, 2026, 4:53 p.m. |
Created at: March 27, 2026, 2:05 p.m.