Triple
T20301970
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Robert Marshak |
E505503
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Marshak |
—
|
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: Marshak | Statement: [Robert Marshak, familyName, Marshak]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marshak Context triple: [Robert Marshak, familyName, Marshak]
-
A.
Marshak
chosen
Marshak is a surname most notably associated with Robert Marshak, an influential American theoretical physicist and educator.
-
B.
Zaslofsky
Zaslofsky is a surname most notably associated with Max Zaslofsky, an early star guard in the National Basketball Association.
-
C.
Kraushaar
Kraushaar is a surname most notably associated with Raoul Kraushaar, an American film and television composer active in the mid-20th century.
-
D.
Mileikowsky
Mileikowsky is a Jewish family name notably borne by Benzion Mileikowsky, a Zionist activist and scholar and father of Israeli Prime Minister Benjamin Netanyahu.
-
E.
Majchrowski
Majchrowski is a Polish surname most notably borne by Jacek Majchrowski, a long-serving mayor of Kraków and prominent political figure.
- 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_69e0b4b8ab648190906e18538c250148 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6770d82b48190b21ce7c52ec6d5a0 |
completed | April 20, 2026, 6:57 p.m. |
Created at: April 16, 2026, 11:17 a.m.