Triple
T27746423
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Surface 3 |
E701994
|
entity |
| Predicate | supportsTypeCover |
P10512
|
FINISHED |
| Object | Surface 3 Type Cover |
—
|
NE NERFINISHED |
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: Surface 3 Type Cover | Statement: [Surface 3, supportsTypeCover, Surface 3 Type Cover]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsTypeCover Context triple: [Surface 3, supportsTypeCover, Surface 3 Type Cover]
-
A.
hasTypeCoverCompatibility
Indicates that one entity’s type is compatible with, or can be safely covered or substituted by, the type of another entity.
-
B.
supportsType
Indicates that one entity is capable of handling, accepting, or being compatible with a specified type.
-
C.
supportsCustomCovers
Indicates that one entity provides the capability for another entity to use or define custom cover designs or images.
-
D.
hasCoverType
chosen
Indicates that one entity possesses or is associated with a specific type or category of cover.
-
E.
supportsTestType
Indicates that one entity is capable of handling, executing, or being compatible with a specified type of test.
- 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_69ef6a53c7388190899baa6daf42301c |
completed | April 27, 2026, 1:53 p.m. |
| NER | Named-entity recognition | batch_69fff9b126b4819085a4cf8791d388d1 |
completed | May 10, 2026, 3:21 a.m. |
| PD | Predicate disambiguation | batch_69fff8f913a881908d3b7e490d92631f |
completed | May 10, 2026, 3:18 a.m. |
Created at: April 27, 2026, 4:16 p.m.