Triple
T8414359
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ARAnyM |
E198697
|
entity |
| Predicate | supportsSoftwareType |
P24486
|
FINISHED |
| Object | Atari ST software |
—
|
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: Atari ST software | Statement: [ARAnyM, supportsSoftwareType, Atari ST software]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsSoftwareType Context triple: [ARAnyM, supportsSoftwareType, Atari ST software]
-
A.
supportsType
chosen
Indicates that one entity is capable of handling, accepting, or being compatible with a specified type.
-
B.
supportsProgramType
Indicates that one entity is capable of handling, offering, or being compatible with a specified type of program.
-
C.
hasSoftwareCompatibilityWith
Indicates that one software system can operate correctly and effectively with another software system, without conflicts or required modifications.
-
D.
supportsPluginType
Indicates that one entity is capable of working with, handling, or being compatible with a specified type of plugin.
-
E.
supportsSoftwareEcosystem
Indicates that one entity provides resources, compatibility, or infrastructure that enables another entity’s software ecosystem to function, grow, or be maintained.
- 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_69ca831201b481909e137936ef99ff11 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cb83e328cc8190b3b038005d0bb66f |
completed | March 31, 2026, 8:20 a.m. |
| PD | Predicate disambiguation | batch_69cb70d473dc8190af8ea81ee5aa970d |
completed | March 31, 2026, 6:59 a.m. |
Created at: March 30, 2026, 6:06 p.m.