Triple
T22840558
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pieces of Her |
E566066
|
entity |
| Predicate | stars |
P1956
|
FINISHED |
| Object | Joe Dempsie |
—
|
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: Joe Dempsie | Statement: [Pieces of Her, stars, Joe Dempsie]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Joe Dempsie Context triple: [Pieces of Her, stars, Joe Dempsie]
-
A.
Joe Dempsie
chosen
Joe Dempsie is a British actor best known for his roles in the TV series Skins and Game of Thrones.
-
B.
George Eads
George Eads is an American actor best known for his long-running role as Nick Stokes on the television series CSI: Crime Scene Investigation.
-
C.
Holt McCallany
Holt McCallany is an American actor best known for his tough, authoritative roles in film and television, including a prominent turn as FBI agent Bill Tench in the series "Mindhunter."
-
D.
Peter Macon
Peter Macon is an American actor best known for playing the Moclan officer Lt. Cmdr. Bortus on the science fiction comedy-drama series "The Orville."
-
E.
James Purefoy
James Purefoy is an English actor known for his roles in film and television, including prominent performances in series such as "Rome" and "The Following."
- 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_69e245869e188190a196584f36e682da |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17e83fa48819084568264ef45c833 |
completed | April 29, 2026, 3:44 a.m. |
Created at: April 17, 2026, 3:35 p.m.