Triple
T38566187
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Power Macintosh 7300 |
E928222
|
entity |
| Predicate | supportedDisplays |
P76291
|
FINISHED |
| Object | Apple multiple-scan and fixed-frequency monitors |
—
|
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: Apple multiple-scan and fixed-frequency monitors | Statement: [Power Macintosh 7300, supportedDisplays, Apple multiple-scan and fixed-frequency monitors]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportedDisplays Context triple: [Power Macintosh 7300, supportedDisplays, Apple multiple-scan and fixed-frequency monitors]
-
A.
supportsDisplayTechnology
chosen
Indicates that one entity is compatible with, or capable of operating using, a specified display technology.
-
B.
availableDisplaySizes
Indicates the set of display size options that can be provided or used for a given entity.
-
C.
canBeDisplayedOn
Indicates that something is capable of being shown or rendered on a particular medium, device, or interface.
-
D.
supportsDisplayResolution
Indicates that one entity is capable of operating with, rendering, or otherwise accommodating the specified display resolution of another entity.
-
E.
supportsDisplayStandard
Indicates that one entity is compatible with and can correctly handle or render the specified display standard.
- 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_69f76eb8d1808190a588af29d8b266d6 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a037c903be48190a2fafa53d7d50d42 |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a1e32108190897356d6a7fed879 |
completed | May 12, 2026, 7:06 p.m. |
Created at: May 3, 2026, 4:32 p.m.