Triple
T4298719
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sheldon Leonard |
E99778
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object |
Bershad
Bershad is the surname of American actor, producer, and director Sheldon Leonard, known for his influential work in mid-20th-century film and television.
|
E429949
|
NE FINISHED |
How this triple was built (4 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: Bershad | Statement: [Sheldon Leonard, familyName, Bershad]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bershad Context triple: [Sheldon Leonard, familyName, Bershad]
-
A.
Rosenbad
Rosenbad is a prominent government building complex in central Stockholm that houses the offices of the Prime Minister and the Swedish Government.
-
B.
Shakhlin
Shakhlin is the surname of Boris Shakhlin, a celebrated Soviet artistic gymnast and multiple Olympic champion.
-
C.
Bierut
Bierut is a Polish surname most notably associated with Bolesław Bierut, a communist politician who served as the leader of postwar Poland.
-
D.
Erlikh
Erlikh is an alternative transliteration or spelling variant of the surname Ehrlich, commonly found in Germanic and Jewish contexts.
-
E.
Zaslofsky
Zaslofsky is a surname most notably associated with Max Zaslofsky, an early star guard in the National Basketball Association.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Bershad Triple: [Sheldon Leonard, familyName, Bershad]
Generated description
Bershad is the surname of American actor, producer, and director Sheldon Leonard, known for his influential work in mid-20th-century film and television.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Bershad Target entity description: Bershad is the surname of American actor, producer, and director Sheldon Leonard, known for his influential work in mid-20th-century film and television.
-
A.
Rosenbad
Rosenbad is a prominent government building complex in central Stockholm that houses the offices of the Prime Minister and the Swedish Government.
-
B.
Shakhlin
Shakhlin is the surname of Boris Shakhlin, a celebrated Soviet artistic gymnast and multiple Olympic champion.
-
C.
Bierut
Bierut is a Polish surname most notably associated with Bolesław Bierut, a communist politician who served as the leader of postwar Poland.
-
D.
Erlikh
Erlikh is an alternative transliteration or spelling variant of the surname Ehrlich, commonly found in Germanic and Jewish contexts.
-
E.
Zaslofsky
Zaslofsky is a surname most notably associated with Max Zaslofsky, an early star guard in the National Basketball Association.
- F. None of above. chosen
Provenance (5 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_69b3455175088190aa79c6e03b86647e |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b3509d39348190aa83304661230cba |
completed | March 12, 2026, 11:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5c746c9108190a1a81e94b4768f3c |
completed | March 14, 2026, 8:38 p.m. |
| NEDg | Description generation | batch_69b5c929aec48190bb9a00b7086afe01 |
completed | March 14, 2026, 8:46 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b5c993a9388190a52e573b013dbe29 |
completed | March 14, 2026, 8:48 p.m. |
Created at: March 12, 2026, 11:08 p.m.