Triple
T2713738
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fall |
E59918
|
entity |
| Predicate | hasStreamingFormat |
P8462
|
FINISHED |
| Object | digital download |
—
|
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: digital download | Statement: [Fall, hasStreamingFormat, digital download]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasStreamingFormat Context triple: [Fall, hasStreamingFormat, digital download]
-
A.
hasProductionFormat
Indicates that an entity is associated with, or presented in, a particular production or media format.
-
B.
hasFileFormat
chosen
Indicates that one entity (typically a digital file or resource) is encoded, stored, or represented using a specific file format defined by the other entity.
-
C.
operatesInFormat
Indicates that an entity functions, performs its role, or is carried out using a specified format.
-
D.
broadcastsInFormat
Indicates that a broadcasting entity transmits its content using a specified technical format or standard.
-
E.
hasMediaAdaptation
Indicates that a work has been adapted into another medium, such as film, television, or other forms of media.
- 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_69ab4ac92a088190bc74bca14038e3de |
completed | March 6, 2026, 9:44 p.m. |
| NER | Named-entity recognition | batch_69abda924b24819090adc4128e86d4bd |
completed | March 7, 2026, 7:58 a.m. |
| PD | Predicate disambiguation | batch_69abd8224c688190bb4a362360b03007 |
completed | March 7, 2026, 7:47 a.m. |
Created at: March 6, 2026, 9:55 p.m.