Triple
T23032768
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | King Richard |
E573508
|
entity |
| Predicate | writer |
P1360
|
FINISHED |
| Object | Zach Baylin |
—
|
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: Zach Baylin | Statement: [King Richard, writer, Zach Baylin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Zach Baylin Context triple: [King Richard, writer, Zach Baylin]
-
A.
Zach Baylin
chosen
Zach Baylin is an American screenwriter best known for his work on acclaimed sports dramas such as King Richard and Creed III.
-
B.
Zachary Greenburg
Zachary Greenburg is the son of American author and humorist Dan Greenburg.
-
C.
Zerach Barnett
Zerach Barnett was a Jewish scholar and author known for his religious writings and contributions to Torah study.
-
D.
Zachary Sklar
Zachary Sklar is an American screenwriter and journalist best known for co-writing Oliver Stone’s political thriller film "JFK."
-
E.
Zachary LeVine
Zachary LeVine is an actor best known for his role in the independent dark comedy film "Spanking the Monkey."
- 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_69e245b911188190bc3d96326c847969 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18482e78c8190a89681eec2edb812 |
completed | April 29, 2026, 4:09 a.m. |
Created at: April 17, 2026, 3:53 p.m.