Triple
T21947890
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bird |
E541980
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Joel Oliansky |
—
|
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: Joel Oliansky | Statement: [Bird, screenwriter, Joel Oliansky]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Joel Oliansky Context triple: [Bird, screenwriter, Joel Oliansky]
-
A.
Joel Oliansky
chosen
Joel Oliansky was an American screenwriter and director known for his work in film and television during the 1960s–1980s, including the screenplay for the thriller "Counterpoint."
-
B.
Joel Benjamin
Joel Benjamin is an American chess grandmaster and author who notably served as a consultant for IBM's Deep Blue computer in its historic matches against Garry Kasparov.
-
C.
Joel Engel
Joel Engel is a notable individual recognized for achievements significant enough to distinguish him among others sharing the surname Engel.
-
D.
Joel Springer
Joel Springer is known primarily as the husband of award-winning American mystery and fantasy author Nancy Springer.
-
E.
Joel Corelitz
Joel Corelitz is an American composer and sound designer known for his atmospheric, experimental scores for video games and interactive media.
- 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_69e0c47ef0e48190a50e1bcc43f4b3fd |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f1243a2f788190bd4625fa79888696 |
completed | April 28, 2026, 9:18 p.m. |
Created at: April 16, 2026, 7:57 p.m.