Triple
T27636694
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MatSort |
E696489
|
entity |
| Predicate | unregisters |
P70879
|
FINISHED |
| Object | MatSortable instances |
—
|
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: MatSortable instances | Statement: [MatSort, unregisters, MatSortable instances]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: unregisters Context triple: [MatSort, unregisters, MatSortable instances]
-
A.
cancels
chosen
Indicates that one entity invalidates, nullifies, or stops the effect, operation, or scheduled occurrence of another entity or action.
-
B.
UNDesignation
Indicates that an entity has been formally assigned a specific status, role, or classification by the United Nations.
-
C.
withdrewFrom
Indicates that one entity removed itself or its participation from another entity, context, or arrangement it was previously part of.
-
D.
deactivated
Indicates that an entity has been turned off, disabled, or rendered inactive so it no longer performs its usual function or role.
-
E.
renouncedBy
Indicates that an entity has been formally rejected, disowned, or given up by another 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_69ef5909f3848190805f35b76833e722 |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69f6318d4f2c81908fe25c3dd5d68e94 |
completed | May 2, 2026, 5:17 p.m. |
| PD | Predicate disambiguation | batch_69f62c1921008190a62675a31f66a875 |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 27, 2026, 2:24 p.m.