Triple
T20820846
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mark Addy |
E512568
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Mark Addy |
—
|
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: Mark Addy | Statement: [Mark Addy, name, Mark Addy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mark Addy Context triple: [Mark Addy, name, Mark Addy]
-
A.
Mark Addy
chosen
Mark Addy is a British actor best known for roles in films like "The Full Monty" and the TV series "Game of Thrones," where he played King Robert Baratheon.
-
B.
Graham Knight
Graham Knight is a musician best known as a member of the Scottish pop rock band The Marmalade.
-
C.
Peter Armitage
Peter Armitage was a British actor best known for his long-running role as Bill Webster in the soap opera "Coronation Street."
-
D.
Steve Cavanagh
Steve Cavanagh is a Northern Irish crime novelist and former lawyer best known for his Eddie Flynn legal thriller series.
-
E.
Andrew Sagar
Andrew Sagar is a film editor known for his work on the movie "The Rage."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4ce39108190a6e8e5df4f1c8dc5 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c2f7a1548190b6ef3f1cfad37c1c |
completed | April 21, 2026, 12:21 a.m. |
Created at: April 16, 2026, 12:41 p.m.