Triple
T4239663
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ESPN UK |
E94779
|
entity |
| Predicate | broadcastContent |
P17106
|
FINISHED |
| Object | live sports |
—
|
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: live sports | Statement: [ESPN UK, broadcastContent, live sports]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: broadcastContent Context triple: [ESPN UK, broadcastContent, live sports]
-
A.
broadcastType
Indicates the specific mode or category of broadcasting used to transmit content (e.g., live, recorded, streaming, or other broadcast formats) between entities.
-
B.
broadcastVia
chosen
Indicates that an action, message, or content is transmitted or disseminated through a specified medium, channel, or platform.
-
C.
broadcastModel
Indicates that one entity serves as the template or source whose structure or values are replicated and applied across another entity or set of entities.
-
D.
broadcastBlock
Indicates that one entity transmits or disseminates a block (such as a data block or message) to multiple recipients or across a network.
-
E.
broadcastFor
Indicates that one entity transmits or disseminates content, information, or a signal on behalf of, or in service of, 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_69b34537cc6481909cd0a96acbb33ef7 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b34e77fb5c8190b298818acb68ff63 |
completed | March 12, 2026, 11:38 p.m. |
| PD | Predicate disambiguation | batch_69b347f587148190a1830503459939b6 |
completed | March 12, 2026, 11:10 p.m. |
Created at: March 12, 2026, 11:05 p.m.