Triple
T3660170
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lyonel Feininger |
E77628
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object |
Lyonel
Lyonel is a masculine given name most notably borne by the German-American painter and caricaturist Lyonel Feininger.
|
E378001
|
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: Lyonel | Statement: [Lyonel Feininger, givenName, Lyonel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lyonel Context triple: [Lyonel Feininger, givenName, Lyonel]
-
A.
Jules Munshin
Jules Munshin was an American comic actor and singer best known for his energetic musical-comedy roles in mid-20th-century Hollywood films and on Broadway.
-
B.
Léon Zitrone
Léon Zitrone was a prominent French television journalist and news anchor, renowned for his long career presenting news and major public events on French national TV.
-
C.
Ibram Lassaw
Ibram Lassaw was an American abstract sculptor known for his openwork, welded metal constructions and his role in the New York School of Abstract Expressionism.
-
D.
Dashiell Weinstein
Dashiell Weinstein is one of the children of disgraced film producer Harvey Weinstein.
-
E.
Gerard Malanga
Gerard Malanga is an American poet, photographer, and filmmaker closely associated with Andy Warhol and the 1960s New York avant-garde scene.
- 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: Lyonel Triple: [Lyonel Feininger, givenName, Lyonel]
Generated description
Lyonel is a masculine given name most notably borne by the German-American painter and caricaturist Lyonel Feininger.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Lyonel Target entity description: Lyonel is a masculine given name most notably borne by the German-American painter and caricaturist Lyonel Feininger.
-
A.
Jules Munshin
Jules Munshin was an American comic actor and singer best known for his energetic musical-comedy roles in mid-20th-century Hollywood films and on Broadway.
-
B.
Léon Zitrone
Léon Zitrone was a prominent French television journalist and news anchor, renowned for his long career presenting news and major public events on French national TV.
-
C.
Ibram Lassaw
Ibram Lassaw was an American abstract sculptor known for his openwork, welded metal constructions and his role in the New York School of Abstract Expressionism.
-
D.
Dashiell Weinstein
Dashiell Weinstein is one of the children of disgraced film producer Harvey Weinstein.
-
E.
Gerard Malanga
Gerard Malanga is an American poet, photographer, and filmmaker closely associated with Andy Warhol and the 1960s New York avant-garde scene.
- 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_69ad85dfc4dc8190a441864202ab2a7a |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc3d5e5f881909c7c105827d41071 |
completed | March 8, 2026, 6:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b48844a380819084c4627a95b4cb3c |
completed | March 13, 2026, 9:57 p.m. |
| NEDg | Description generation | batch_69b48b1e425481908da667914d1a71e6 |
completed | March 13, 2026, 10:09 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b4aefb58448190b7d34343a5dbb0f6 |
completed | March 14, 2026, 12:42 a.m. |
Created at: March 8, 2026, 3:25 p.m.