Triple
T20467014
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oded Fehr |
E502077
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Fehr |
—
|
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: Fehr | Statement: [Oded Fehr, familyName, Fehr]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fehr Context triple: [Oded Fehr, familyName, Fehr]
-
A.
Fehr
chosen
Fehr is a surname most prominently associated with Donald Fehr, the longtime executive director of the Major League Baseball Players Association and later the NHL Players’ Association.
-
B.
Fichtner
Fichtner is a German-origin surname most notably associated with American character actor William Fichtner, known for his roles in film and television.
-
C.
Schaefer
Schaefer is a German-origin surname commonly borne by individuals of German or Central European descent.
-
D.
Furst
Furst is a surname most notably associated with Anton Furst, the Academy Award–winning production designer known for his work on films like "Batman" (1989).
-
E.
Fischel
Fischel is the birth name of Fred Lebow, the Romanian-American founder and long-time director of the New York City Marathon.
- 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_69e0b4ae5f1081908768b0c9a3a0bf38 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6995d9d1c81909ee223a35a0850ba |
completed | April 20, 2026, 9:23 p.m. |
Created at: April 16, 2026, 11:33 a.m.