Triple
T5354463
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gondwana |
E102656
|
entity |
| Predicate | positionWithinPangaea |
P54605
|
FINISHED |
| Object | southern part |
—
|
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: southern part | Statement: [Gondwana, positionWithinPangaea, southern part]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionWithinPangaea Context triple: [Gondwana, positionWithinPangaea, southern part]
-
A.
paleogeographicAffinity
chosen
Indicates a relationship where entities share or are associated with a particular ancient geographic region or configuration of the Earth's surface.
-
B.
locatedInGeologicPast
Indicates that something existed or occurred in a specific place during a past geologic time period.
-
C.
hasPlateTectonics
Indicates that a planetary body exhibits active plate tectonics, with its outer shell divided into moving plates that interact over geological time.
-
D.
continentOfActivity
Indicates the continent on which an entity primarily operates, is active, or conducts its main activities.
-
E.
locatedOnTectonicPlate
Indicates that one entity (typically a geographic region or feature) lies upon or is situated on the tectonic plate represented by the other entity.
- 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_69bd43d8f7248190b64c140734b5c9a8 |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd862dbb008190aef653acddafd38b |
completed | March 20, 2026, 5:38 p.m. |
| PD | Predicate disambiguation | batch_69bd845c6f108190832a8d14b356368a |
completed | March 20, 2026, 5:31 p.m. |
Created at: March 20, 2026, 2:01 p.m.