Triple
T9502524
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sony α1 |
E229179
|
entity |
| Predicate | effectiveResolution |
P33931
|
FINISHED |
| Object | 50.1 megapixels |
—
|
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: 50.1 megapixels | Statement: [Sony α1, effectiveResolution, 50.1 megapixels]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: effectiveResolution Context triple: [Sony α1, effectiveResolution, 50.1 megapixels]
-
A.
hasResolution
chosen
Indicates that one entity possesses, specifies, or is associated with a particular level or type of resolution (such as detail, clarity, or granularity) in relation to another entity.
-
B.
resolutionLeadsTo
Indicates that achieving a particular resolution or decision directly brings about or causes a subsequent outcome or state.
-
C.
resolution
Indicates the act of formally deciding, settling, or expressing a determined stance on an issue, often through an official decision or statement.
-
D.
targetResolution
Indicates the specific resolution or level of detail that an action, process, or system is intended to achieve or operate at.
-
E.
resolutionCommon
Indicates that multiple entities share the same resolution or level of detail in a given context.
- 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_69ca847611c48190a28c028644198c75 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd983ea6048190a2d7924c8e6d1fbc |
completed | April 1, 2026, 10:12 p.m. |
| PD | Predicate disambiguation | batch_69cca5651a588190a3cfebe249a223e5 |
completed | April 1, 2026, 4:56 a.m. |
Created at: March 30, 2026, 7:57 p.m.