Triple
T14047530
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Adele Romanski |
E337996
|
entity |
| Predicate | foundedByTogetherWith |
P4562
|
FINISHED |
| Object | Mark Ceryak |
E761027
|
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: Mark Ceryak | Statement: [Adele Romanski, foundedByTogetherWith, Mark Ceryak]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mark Ceryak Context triple: [Adele Romanski, foundedByTogetherWith, Mark Ceryak]
-
A.
Mark Ceryak
chosen
Mark Ceryak is a film and television producer best known for his work on the acclaimed series "The Underground Railroad."
-
B.
Michael Cerenzie
Michael Cerenzie is a film producer known for his work on independent and genre films in Hollywood.
-
C.
Mark Korven
Mark Korven is a Canadian film and television composer best known for his unsettling, atmospheric scores for horror projects such as The Witch and The Lighthouse.
-
D.
Mark Czyzewski
Mark Czyzewski is an editor known for his work on the film "Greyhound."
-
E.
Gregory Tsamblak
Gregory Tsamblak was a medieval Orthodox cleric, writer, and scholar of Bulgarian origin who became a prominent church leader and man of letters in the Slavic world.
- 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_69d81c664e48819088cbd8f433aeffe5 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de3c88b5e48190b0f0149102c08992 |
completed | April 14, 2026, 1:09 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcb65c1a90819097754497f07f5312 |
completed | May 7, 2026, 3:57 p.m. |
Created at: April 9, 2026, 10:20 p.m.