Triple
T20388102
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Small Crimes |
E498009
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Nikolaj Coster-Waldau |
—
|
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: Nikolaj Coster-Waldau | Statement: [Small Crimes, starring, Nikolaj Coster-Waldau]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nikolaj Coster-Waldau Context triple: [Small Crimes, starring, Nikolaj Coster-Waldau]
-
A.
Nikolaj Coster-Waldau
chosen
Nikolaj Coster-Waldau is a Danish actor best known internationally for his role as Jaime Lannister in the television series "Game of Thrones."
-
B.
Jonathan Rhys Hill
Jonathan Rhys Hill is a composer best known for his work on television drama scores, including the series "The Trial of Christine Keeler."
-
C.
Joe Dempsie
Joe Dempsie is a British actor best known for his roles in the TV series Skins and Game of Thrones.
-
D.
Josh Charles
Josh Charles is an American actor best known for his roles in films like Dead Poets Society and the television series The Good Wife.
-
E.
Nukâka Coster-Waldau
Nukâka Coster-Waldau is a Greenlandic actress and singer who has appeared in film, television, and theater productions.
- 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_69e0b4a71ebc8190b153a36c738730f4 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6790d9e5881908bde7da9e5e541a0 |
completed | April 20, 2026, 7:05 p.m. |
Created at: April 16, 2026, 11:28 a.m.