Triple
T16041605
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Torry Holt |
E389108
|
entity |
| Predicate | broadcastingWork |
P121715
|
FINISHED |
| Object | football analyst |
—
|
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: football analyst | Statement: [Torry Holt, broadcastingWork, football analyst]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: broadcastingWork Context triple: [Torry Holt, broadcastingWork, football analyst]
-
A.
broadcastNetwork
Indicates that one entity serves as the television or radio network that broadcasts the programming or content of another entity.
-
B.
broadcastsIn
Indicates that one entity transmits or airs content within a particular medium, channel, location, or time frame.
-
C.
broadcastProgram
Indicates that a media outlet or channel transmits a specific program to an audience via a broadcast medium.
-
D.
broadcastsTo
Indicates that one entity transmits or disseminates information, signals, or content to another entity or group of entities.
-
E.
broadcastService
Indicates that one entity provides or is associated with a broadcast service used to distribute media or information to an audience.
- 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_69d86dada3808190825d5f80d72fbe88 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1ff63edb0819092cbb671967bbdcd |
completed | April 17, 2026, 9:37 a.m. |
| PD | Predicate disambiguation | batch_69e1826f34c081908005bb736f1c485d |
completed | April 17, 2026, 12:44 a.m. |
| PDg | Predicate description generation | batch_69e1ff5cd7e481908a29214139a3de2e |
completed | April 17, 2026, 9:37 a.m. |
Created at: April 10, 2026, 4:56 a.m.