Triple
T8122406
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ed Byrne |
E189639
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Ed Byrne |
E189639
|
NE 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: Ed Byrne | Statement: [Ed Byrne, name, Ed Byrne]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ed Byrne Context triple: [Ed Byrne, name, Ed Byrne]
-
A.
Ed Byrne
chosen
Ed Byrne is an Irish stand-up comedian and actor known for his observational humor and frequent appearances on British television panel shows.
-
B.
Andrew McGahan
Andrew McGahan was an acclaimed Australian novelist and screenwriter known for his darkly comic and socially incisive works, including the Miles Franklin Award–winning novel "The White Earth."
-
C.
Stuart Maynard
Stuart Maynard is an English football manager best known for managing Notts County F.C. in the lower tiers of the English football league system.
-
D.
Ed Shearmur
Ed Shearmur is a British film composer known for scoring a wide range of Hollywood movies across genres.
-
E.
Chris Bremner
Chris Bremner is a screenwriter best known for his work on major Hollywood action-comedy films, including entries in the Bad Boys franchise.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca82bb74848190afb1f18640632c10 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb435cb30881909ccaa2f625e53799 |
completed | March 31, 2026, 3:45 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cc945c743c8190bf1d8e60975bd8bc |
completed | April 1, 2026, 3:43 a.m. |
Created at: March 30, 2026, 5:33 p.m.