Triple
T30811290
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nikon Z 9 |
E784650
|
entity |
| Predicate | hdmiPort |
P85051
|
FINISHED |
| Object | full-size HDMI |
—
|
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: full-size HDMI | Statement: [Nikon Z 9, hdmiPort, full-size HDMI]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hdmiPort Context triple: [Nikon Z 9, hdmiPort, full-size HDMI]
-
A.
hasHDMIPort
chosen
Indicates that one entity (typically a device) is equipped with an HDMI port that can be used to connect to another entity.
-
B.
hdmiVersion
Indicates the specific HDMI standard or version associated with a device, port, or connection.
-
C.
hasCompositeVideoOutput
Indicates that a device provides a composite video output connection for transmitting standard-definition analog video signals.
-
D.
supportsDisplayPortAltMode
Indicates that one entity is capable of transmitting video and audio using the DisplayPort Alternate Mode over a USB-C or similar connection to another entity.
-
E.
televisionOutlet
Indicates a relationship where an entity functions as a television broadcasting outlet or channel for another entity.
- 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_69f224b4eda48190bd212ce4f3901e56 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f69064ad888190ba223c7dc83bc98e |
completed | May 3, 2026, 12:01 a.m. |
| PD | Predicate disambiguation | batch_69f68b7d2794819092fef8a63f4f3de8 |
completed | May 2, 2026, 11:40 p.m. |
Created at: April 29, 2026, 8:43 p.m.