Triple
T12281027
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AddressSanitizer |
E292715
|
entity |
| Predicate | typicalOverhead |
P103999
|
FINISHED |
| Object | about 2x memory usage |
—
|
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: about 2x memory usage | Statement: [AddressSanitizer, typicalOverhead, about 2x memory usage]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalOverhead Context triple: [AddressSanitizer, typicalOverhead, about 2x memory usage]
-
A.
typicalBase
Indicates that one entity serves as the standard or most representative base or foundation for another entity in typical or common cases.
-
B.
typicalLength
Indicates the usual or characteristic length associated with an entity or phenomenon.
-
C.
typicalCapacity
Indicates the usual or standard amount, volume, or capability that something is designed or expected to hold, handle, or perform under normal conditions.
-
D.
typicalDimension
Indicates that one entity represents a standard or characteristic measurement (such as size, length, or capacity) typically associated with another entity.
-
E.
typicallyHolds
Indicates that a certain relationship or condition generally holds true in typical or normal situations, though not necessarily in all cases.
- F. None of above. chosen
Provenance (4 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_69d6ab690ad081908c0ed3870ec82d53 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d9261e1570819084bb4fdb44aa6aea |
completed | April 10, 2026, 4:32 p.m. |
| PD | Predicate disambiguation | batch_69d91c4d9a9c8190aeb7beaf9792d8f0 |
completed | April 10, 2026, 3:50 p.m. |
| PDg | Predicate description generation | batch_69d9261b7f088190b69fe6961015fce3 |
completed | April 10, 2026, 4:32 p.m. |
Created at: April 8, 2026, 9:52 p.m.