Triple
T20472083
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The 33 |
E502217
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Mikko Alanne |
—
|
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: Mikko Alanne | Statement: [The 33, screenwriter, Mikko Alanne]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mikko Alanne Context triple: [The 33, screenwriter, Mikko Alanne]
-
A.
Mikko Alanne
chosen
Mikko Alanne is a Finnish-American screenwriter and producer known for his work on historical and war-themed films and television series.
-
B.
Mikko Aalto
Mikko Aalto is a Finnish musician best known as the guitarist for the metal band Impaled Nazarene.
-
C.
Jorma Rissanen
Jorma Rissanen was a Finnish information theorist best known for pioneering the Minimum Description Length (MDL) principle and making foundational contributions to data compression and statistical modeling.
-
D.
Mikko Kodisoja
Mikko Kodisoja is a Finnish entrepreneur best known as a co-founder of the mobile game company Supercell, creator of hits like Clash of Clans and Hay Day.
-
E.
Jorma Panula
Jorma Panula is a renowned Finnish conductor and conducting pedagogue, celebrated for training many of the world’s leading conductors.
- 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_69e0b4ae5f1081908768b0c9a3a0bf38 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6996197908190b6570e2a7fd6cf67 |
completed | April 20, 2026, 9:23 p.m. |
Created at: April 16, 2026, 11:33 a.m.