Triple
T20620593
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Flicka |
E506687
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object | Michael Mayer |
—
|
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: Michael Mayer | Statement: [Flicka, director, Michael Mayer]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Mayer Context triple: [Flicka, director, Michael Mayer]
-
A.
Michael Mayer
chosen
Michael Mayer is an acclaimed American theater director known for his innovative work on Broadway musicals and plays, including the Tony Award-winning production of "Spring Awakening."
-
B.
Thomas Meyer
Thomas Meyer is a professional associated with Jonathan Williams as his partner, likely in a business or legal context.
-
C.
Phillip Schneider
Phillip Schneider is a screenwriter best known for his work on the psychological thriller film "Swimfan."
-
D.
Christopher Franke
Christopher Franke is a German composer and former Tangerine Dream member best known for his electronic and film scores, including work on science fiction and adventure productions.
-
E.
Michael Berg
Michael Berg is the introspective German protagonist of Bernhard Schlink’s novel *The Reader*, whose adolescent affair with an older woman shapes his moral and emotional development amid the legacy of the Holocaust.
- 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_69e0b4bc90988190ac360aaf645efc1d |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6abe19ca481908c896bec49a025cd |
completed | April 20, 2026, 10:42 p.m. |
Created at: April 16, 2026, 11:42 a.m.