Triple
T30432591
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | macOS on Apple silicon |
E774211
|
entity |
| Predicate | firstSupportedHardware |
P203842
|
FINISHED |
| Object | MacBook Air (M1, 2020) |
E38962
|
NE 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: MacBook Air (M1, 2020) | Statement: [macOS on Apple silicon, firstSupportedHardware, MacBook Air (M1, 2020)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstSupportedHardware Context triple: [macOS on Apple silicon, firstSupportedHardware, MacBook Air (M1, 2020)]
-
A.
firstSupportedBy
Indicates that an entity is initially upheld, enabled, or made possible by another entity that provides its primary support.
-
B.
previouslySupportedHardware
Indicates that the subject hardware was supported in the past but is no longer currently supported.
-
C.
firstSupportedCPUCore
Indicates the CPU core that initially provided support or capability for a given feature, process, or entity.
-
D.
hasHardwareCompatibilityWith
Indicates that two hardware components or systems can operate together correctly and reliably without conflicts or incompatibilities.
-
E.
firstSupportedMicroarchitecture
Indicates the earliest or oldest microarchitecture that provides support for a given hardware or software feature.
- F. None of above. chosen
Provenance (5 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_69f22492d2a88190995ce8745d9becaa |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_6a02206665508190ae2324d253ccf377 |
completed | May 11, 2026, 6:31 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a2798bbe8408190b2efbf698e1ec015 |
completed | June 9, 2026, 4:38 a.m. |
| PD | Predicate disambiguation | batch_6a021fdc6e54819082847bedd97a680b |
completed | May 11, 2026, 6:28 p.m. |
| PDg | Predicate description generation | batch_6a0220656d9c819088d57951a96423b8 |
completed | May 11, 2026, 6:31 p.m. |
Created at: April 29, 2026, 8:07 p.m.