Triple
T28148842
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ed Byrne: Uncut |
E714555
|
entity |
| Predicate | featuresCountryOfComedian |
P107111
|
FINISHED |
| Object | Ireland |
—
|
NE NERFINISHED |
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: Ireland | Statement: [Ed Byrne: Uncut, featuresCountryOfComedian, Ireland]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresCountryOfComedian Context triple: [Ed Byrne: Uncut, featuresCountryOfComedian, Ireland]
-
A.
countryOf
Indicates that one entity is the country to which another entity belongs, is located in, or is associated with.
-
B.
nationalityOfActor
Indicates that a specified nationality is associated with, or belongs to, a particular actor.
-
C.
commentatorCountry
chosen
Indicates the country with which a commentator is associated, such as their nationality or the nation they represent.
-
D.
formationCountry
Indicates the country in which an entity (such as an organization, company, or group) was originally formed or established.
-
E.
countryContributors
Indicates a relationship where certain entities contribute to, support, or provide resources to a specified country.
- 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_69efd6b033208190bf74f80a147e2092 |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_69fe0d165a48819098b854318a50d76c |
completed | May 8, 2026, 4:19 p.m. |
| PD | Predicate disambiguation | batch_69fe0931002481908a95b34f95e9f64e |
completed | May 8, 2026, 4:02 p.m. |
Created at: April 27, 2026, 9:58 p.m.