Triple
T7067603
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Carnival Row |
E164597
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | David Gyasi |
E142449
|
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: David Gyasi | Statement: [Carnival Row, starring, David Gyasi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: David Gyasi Context triple: [Carnival Row, starring, David Gyasi]
-
A.
David Gyasi
chosen
David Gyasi is a British actor known for his roles in films like "Interstellar" and series such as "Troy: Fall of a City" and "Carnival Row."
-
B.
Darius Ogden Mills
Darius Ogden Mills was a prominent 19th-century American banker, financier, and philanthropist influential in the development of California.
-
C.
Daniel Lyons
Daniel Lyons is a fictional character from the British television drama series "Years and Years," portrayed by actor Russell Tovey.
-
D.
David Gianotten
David Gianotten is a Dutch architect and managing partner at the renowned architecture firm OMA, known for leading major international projects and the firm’s overall direction.
-
E.
Alex Gorsky
Alex Gorsky is an American business executive best known for serving as chairman and CEO of Johnson & Johnson.
- 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_69c6887b96548190a8a9b3ac8adf4119 |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e4a737dc8190add7f0228cb28111 |
completed | March 27, 2026, 8:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7944fe5ec819098ff44e2872fc644 |
completed | March 28, 2026, 8:41 a.m. |
Created at: March 27, 2026, 2:39 p.m.