Triple
T20929112
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Richard Donner |
E515421
|
entity |
| Predicate | birthSurname |
P18
|
FINISHED |
| Object | Schwartzberg |
—
|
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: Schwartzberg | Statement: [Richard Donner, birthSurname, Schwartzberg]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Schwartzberg Context triple: [Richard Donner, birthSurname, Schwartzberg]
-
A.
Schwartzberg
chosen
Schwartzberg is the birth surname of American film director Richard Donner, who was born Richard Donald Schwartzberg.
-
B.
Schatzberg
Schatzberg is a surname most notably associated with Jerry Schatzberg, an American photographer and film director known for works like "Panic in Needle Park" and "Scarecrow."
-
C.
Zaretsky
Zaretsky is a minor character in Alexander Pushkin’s verse novel "Eugene Onegin," known primarily as the experienced and somewhat cynical second in the duel between Onegin and Lensky.
-
D.
Shteynberg
Shteynberg is a variant spelling of the Jewish surname Steinberg, commonly found among Ashkenazi families.
-
E.
Spangenberg
Spangenberg is a small town in Germany, historically situated within the region of Westphalia.
- 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_69e0b4fb431c8190b9d40e6a72f0cc87 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6f653a25c8190adb46f5d764afba7 |
completed | April 21, 2026, 4 a.m. |
Created at: April 16, 2026, 12:49 p.m.