Triple
T10325670
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Old Guard |
E242754
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Harry Melling |
E385516
|
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: Harry Melling | Statement: [The Old Guard, starring, Harry Melling]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Harry Melling Context triple: [The Old Guard, starring, Harry Melling]
-
A.
Harry Melling
chosen
Harry Melling is an English actor known for his role as Dudley Dursley in the Harry Potter film series and for his later work in film and television, including acclaimed character performances in period dramas and thrillers.
-
B.
Rupert Grint
Rupert Grint is an English actor best known for playing Ron Weasley in the Harry Potter film series.
-
C.
Daniel Radcliffe
Daniel Radcliffe is an English actor best known for playing the title role in the Harry Potter film series.
-
D.
Valentine Miller
Valentine Miller is a child of the influential American writer Henry Miller, known for his groundbreaking and controversial novels of the 20th century.
-
E.
Michael Fenton Stevens
Michael Fenton Stevens is a British actor and comedian known for his work in television, radio, and comedy ensembles such as The Hee Bee Gee Bees and Radio Active.
- 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_69d381af787481908bc401325c760a88 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d7cd76348190b93562112300acfc |
completed | April 7, 2026, 10:09 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d71da93b988190ad568b0677b5d344 |
completed | April 9, 2026, 3:31 a.m. |
Created at: April 6, 2026, 11:51 a.m.