Triple
T12621309
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thunderbolt 3 (USB‑C) |
E301384
|
entity |
| Predicate | supportsVideoOutput |
P31524
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [Thunderbolt 3 (USB‑C), supportsVideoOutput, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsVideoOutput Context triple: [Thunderbolt 3 (USB‑C), supportsVideoOutput, true]
-
A.
supportsVideoPlayback
Indicates that an entity is capable of playing or rendering video content.
-
B.
videoOutput
chosen
Indicates that one entity produces or provides video signals or content as output to another entity or medium.
-
C.
videoOutputConnector
Indicates a relationship where a device or component provides a connector used to output video signals to an external display or receiver.
-
D.
hasHDMIPort
Indicates that one entity (typically a device) is equipped with an HDMI port that can be used to connect to another entity.
-
E.
supportsVerticalVideo
Indicates that one entity provides compatibility with or proper handling of vertical (portrait-oriented) video content 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_69d7bdeaf49c8190b13800111fa77ea3 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d9617b07ec8190b714f04ae6654060 |
completed | April 10, 2026, 8:45 p.m. |
| PD | Predicate disambiguation | batch_69d960b195108190ac25bd95e644ace4 |
completed | April 10, 2026, 8:42 p.m. |
Created at: April 9, 2026, 5:14 p.m.