Triple
T635318
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South American Plate |
E16609
|
entity |
| Predicate | separatesFrom |
P1175
|
FINISHED |
| Object | African Plate at Mid-Atlantic Ridge |
—
|
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: African Plate at Mid-Atlantic Ridge | Statement: [South American Plate, separatesFrom, African Plate at Mid-Atlantic Ridge]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: separatesFrom Context triple: [South American Plate, separatesFrom, African Plate at Mid-Atlantic Ridge]
-
A.
separates
chosen
Indicates that one entity divides, parts, or keeps other entities apart from each other.
-
B.
separatedInto
Indicates that something has been divided or split into distinct parts, groups, or components.
-
C.
separatedFunctionFrom
Indicates that one entity has been detached or removed from performing a particular function or role in relation to another entity.
-
D.
dividedBetween
Indicates that something is partitioned or shared among two or more distinct entities or groups.
-
E.
separatedFromOffice
Indicates that an individual has been removed or dismissed from holding a particular office or official 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_69a4936be1c88190af56540324b57da7 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a49ee667f08190a0332b8f6c569e1a |
completed | March 1, 2026, 8:17 p.m. |
| PD | Predicate disambiguation | batch_69a49d0483908190a5ec42a7403c258e |
completed | March 1, 2026, 8:09 p.m. |
Created at: March 1, 2026, 7:35 p.m.