Triple
T18417164
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NHL on ABC |
E441921
|
entity |
| Predicate | usesGraphicsPackageFrom |
P17160
|
FINISHED |
| Object | ESPN NHL coverage |
—
|
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: ESPN NHL coverage | Statement: [NHL on ABC, usesGraphicsPackageFrom, ESPN NHL coverage]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesGraphicsPackageFrom Context triple: [NHL on ABC, usesGraphicsPackageFrom, ESPN NHL coverage]
-
A.
graphics
chosen
Indicates a relationship where one entity is responsible for creating, providing, or handling visual representations or graphical content for another entity or context.
-
B.
graphicsAPI
Indicates a relationship where one entity uses, supports, or is implemented with a particular graphics application programming interface (graphicsAPI).
-
C.
usesGUIFramework
Indicates that one entity employs or is built upon a particular graphical user interface (GUI) framework to provide its visual or interactive functionality.
-
D.
usesGraphType
Indicates that one entity employs or is configured to operate with a specific type of graph representation or graph model.
-
E.
onboardGraphicsModel
Indicates that an entity has a specific integrated or built-in graphics hardware model associated with it.
- 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_69d8b9eb8a508190a942fd75ebd8b1dc |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e51a284b608190b77c360a72aceb7a |
completed | April 19, 2026, 6:08 p.m. |
| PD | Predicate disambiguation | batch_69e469bf7f74819096a01173493412c2 |
completed | April 19, 2026, 5:35 a.m. |
Created at: April 10, 2026, 10:47 a.m.