Triple
T13213670
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mark Jackson |
E314553
|
entity |
| Predicate | roleInBroadcasting |
P14289
|
FINISHED |
| Object | color commentator |
—
|
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: color commentator | Statement: [Mark Jackson, roleInBroadcasting, color commentator]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInBroadcasting Context triple: [Mark Jackson, roleInBroadcasting, color commentator]
-
A.
broadcastRole
chosen
Indicates that an entity has a specific role or function within a broadcast or transmission context.
-
B.
mediaRole
Indicates the specific function, capacity, or position an entity holds in relation to a media item (such as creator, editor, performer, or distributor).
-
C.
broadcasterType
Indicates the category or kind of broadcaster involved in the relationship or action (e.g., public, commercial, online).
-
D.
roleInCanal
Indicates that an entity has a specific functional or organizational role within the context of a canal.
-
E.
roleInVox
Indicates that an entity holds a specific role or function within a Vox-related context, such as a project, system, or organization named or described as "Vox."
- 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_69d806aee7308190b70a237ba2a6e3e1 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98c9f0f148190a0698ef27573c885 |
completed | April 10, 2026, 11:49 p.m. |
| PD | Predicate disambiguation | batch_69d98bc938f081909f123bdf1263ff7f |
completed | April 10, 2026, 11:46 p.m. |
Created at: April 9, 2026, 9:17 p.m.