Triple
T20301964
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marshak |
E505503
|
entity |
| Predicate | notableBearer |
P458
|
FINISHED |
| Object | Robert 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: Robert Marshak | Statement: [Marshak, notableBearer, Robert Marshak]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Robert Marshak Context triple: [Marshak, notableBearer, Robert Marshak]
-
A.
Robert Marshak
chosen
Robert Marshak was an American theoretical physicist known for his contributions to particle physics and for helping to establish the Rochester Conferences, a key series in high-energy physics.
-
B.
Morris Stoloff
Morris Stoloff was an American musical director, conductor, and composer best known for his work on numerous Hollywood film scores during the mid-20th century.
-
C.
Leonid Sherwood
Leonid Sherwood was a Russian architect best known for designing the neo-Gothic cliffside castle Swallow’s Nest in Crimea.
-
D.
George Placzek
George Placzek was a Czech physicist known for his influential work in nuclear physics and quantum theory, including key contributions to early nuclear reactor research.
-
E.
Daniel Syrkin
Daniel Syrkin is an Israeli film and television director known for his work on acclaimed series and feature films, including the espionage drama "Tehran."
- 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.