Triple
T30842947
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Leica screw-mount lenses (via adapter on M bodies) |
E785559
|
entity |
| Predicate | supportsFocusControl |
P207313
|
FINISHED |
| Object | manual focus |
—
|
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: manual focus | Statement: [Leica screw-mount lenses (via adapter on M bodies), supportsFocusControl, manual focus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsFocusControl Context triple: [Leica screw-mount lenses (via adapter on M bodies), supportsFocusControl, manual focus]
-
A.
supportsCameraControl
Indicates that one entity provides functionality for another entity to remotely manage or adjust camera settings or operations.
-
B.
requiresFocus
Indicates that performing or engaging with something demands concentrated attention or mental effort.
-
C.
supportsSoftwareControl
Indicates that one entity enables or is compatible with the management, operation, or regulation of another entity through software-based control mechanisms.
-
D.
focusModeSwitch
Indicates switching the state of an entity into or out of a designated focus mode.
-
E.
supportsImmediateControl
Indicates that one entity enables or allows another entity to exercise direct, real-time control over it without intermediate steps or delays.
- F. None of above. chosen
Provenance (4 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_69f224b850848190a4af4ccf8ddadcdf |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_6a037c9141dc819098d7fcc36e69882c |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a0379e2fac0819089b522db3260028c |
completed | May 12, 2026, 7:05 p.m. |
| PDg | Predicate description generation | batch_6a037c7ee0388190a29faeb5cdb0950a |
completed | May 12, 2026, 7:16 p.m. |
Created at: April 29, 2026, 8:45 p.m.