Triple
T21200098
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Antarctic ice shelves |
E522431
|
entity |
| Predicate | floatOn |
P137883
|
FINISHED |
| Object | ocean water |
—
|
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: ocean water | Statement: [Antarctic ice shelves, floatOn, ocean water]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: floatOn Context triple: [Antarctic ice shelves, floatOn, ocean water]
-
A.
floatType
Indicates that an entity has a specific floating-point data type or is categorized as a floating-point numeric value.
-
B.
floatedOn
chosen
Indicates that one entity was supported by and moved on the surface of a liquid or fluid medium.
-
C.
floatCreators
Indicates that one or more entities are responsible for creating or designing a float, such as those used in parades or similar events.
-
D.
freeFloatAdjustment
Indicates an adjustment made to account for the portion of shares that are freely tradable (free float), typically modifying a value or metric based on the free-float share base.
-
E.
refloated
Indicates that something previously afloat but no longer buoyant has been returned to a floating condition, typically by refilling with air or restoring buoyancy.
- 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_69e0b5112d8881909510b2dcdc93106d |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e7342fe3a08190b7ed2cadf60091a8 |
completed | April 21, 2026, 8:24 a.m. |
| PD | Predicate disambiguation | batch_69e5f6094e3c81909ee9699e00d371f7 |
completed | April 20, 2026, 9:46 a.m. |
Created at: April 16, 2026, 3:18 p.m.