Triple
T17657345
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fimbul Ice Shelf |
E440158
|
entity |
| Predicate | hasCoordinatesApprox |
P10760
|
FINISHED |
| Object | around 70°S 0°E |
—
|
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: around 70°S 0°E | Statement: [Fimbul Ice Shelf, hasCoordinatesApprox, around 70°S 0°E]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCoordinatesApprox Context triple: [Fimbul Ice Shelf, hasCoordinatesApprox, around 70°S 0°E]
-
A.
hasApproximateCoordinates
chosen
Indicates that an entity is associated with location coordinates that are estimated or imprecise rather than exact.
-
B.
hasCoordinates
Indicates that an entity is associated with specific spatial coordinates that define its position in a given reference system.
-
C.
hasApproximateLocation
Indicates that an entity is associated with a location that is known only imprecisely or within a general area rather than an exact position.
-
D.
hasCoordinatePrecision
Indicates the degree of exactness or granularity with which an entity’s spatial coordinates are specified.
-
E.
hasCoordinatesType
Indicates that an entity is associated with a specific type or system of coordinates used to define its position.
- 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_69d8b9e87e18819087104a44dc4dc5b1 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e46ea2b3308190b9ad752728d98856 |
completed | April 19, 2026, 5:56 a.m. |
| PD | Predicate disambiguation | batch_69e3cddc87188190ac2f049b86038676 |
completed | April 18, 2026, 6:30 p.m. |
Created at: April 10, 2026, 9:27 a.m.