Triple
T23477192
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Police Academy |
E570294
|
entity |
| Predicate | stars |
P1956
|
FINISHED |
| Object | David Graf |
—
|
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: David Graf | Statement: [Police Academy, stars, David Graf]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: David Graf Context triple: [Police Academy, stars, David Graf]
-
A.
David Graf
chosen
David Graf was an American character actor best known for his comedic role as the gun-obsessed Officer Eugene Tackleberry in the Police Academy film series.
-
B.
Robert Graf
Robert Graf is a film and television producer best known for his work on major projects such as the sports drama "Battle of the Sexes."
-
C.
David Kaemmer
David Kaemmer is a video game designer and programmer best known as the co-founder of Papyrus Design Group and iRacing, where he created influential racing simulation games.
-
D.
Daniel Koestner
Daniel Koestner is a composer best known for his work on the indie video game Donut County.
-
E.
Daniel Roher
Daniel Roher is a Canadian documentary filmmaker best known for directing the Oscar-winning political documentary "Navalny."
- 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_69e245af8a88819084f2704f6d265a92 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1a74dbea8819085ca84391039e7f7 |
completed | April 29, 2026, 6:38 a.m. |
Created at: April 17, 2026, 6:01 p.m.