Triple
T8750727
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AHL TV streaming |
E207950
|
entity |
| Predicate | supportsQuality |
P85179
|
FINISHED |
| Object | high-definition video |
—
|
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: high-definition video | Statement: [AHL TV streaming, supportsQuality, high-definition video]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsQuality Context triple: [AHL TV streaming, supportsQuality, high-definition video]
-
A.
requiresQuality
Indicates that one entity depends on or needs another entity to possess a specific quality or attribute in order for a condition, action, or relationship to hold.
-
B.
supportsAudioQuality
Indicates that one entity provides or is compatible with a specified level or type of audio quality for another entity or context.
-
C.
associatedWithQuality
Indicates that an entity is linked to, characterized by, or possesses a particular quality or attribute.
-
D.
storageQuality
Indicates the degree or standard of how well something is stored, such as its preservation, safety, or suitability for use.
-
E.
supportsMaterial
Indicates that one entity provides structural or functional support to a material entity, enabling it to be held, stabilized, or borne.
- 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_69ca835bb2bc819084bb5906cb6ef7f8 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc5da5d474819084ae81d21a5089fa |
completed | March 31, 2026, 11:49 p.m. |
| PD | Predicate disambiguation | batch_69cc5c160dac8190b4aeb4bf0529de52 |
completed | March 31, 2026, 11:43 p.m. |
| PDg | Predicate description generation | batch_69cc5cfddef48190aee764ee7b25bae9 |
completed | March 31, 2026, 11:47 p.m. |
Created at: March 30, 2026, 6:39 p.m.