Triple
T17146758
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Under the Sea-Wind |
E416109
|
entity |
| Predicate | illustrator |
P9707
|
FINISHED |
| Object | Howard Frech |
E416109
|
NE FINISHED |
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: Howard Frech | Statement: [Under the Sea-Wind, illustrator, Howard Frech]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Howard Frech Context triple: [Under the Sea-Wind, illustrator, Howard Frech]
-
A.
Howard Frech
chosen
Howard Frech was an illustrator known for providing the artwork for Rachel Carson’s nature book "Under the Sea-Wind."
-
B.
Walter Frentz
Walter Frentz was a German cameraman and filmmaker known for his close collaboration with Leni Riefenstahl and his work on Nazi propaganda films.
-
C.
John Jürgens
John Jürgens is a German singer and actor best known as the son of renowned Austrian composer and entertainer Udo Jürgens.
-
D.
Michael Schaefer
Michael Schaefer is a film and television producer known for his executive production work on projects such as the series "Swarm."
-
E.
Max Rostal
Max Rostal was a prominent 20th-century violinist and influential pedagogue known for his interpretations of classical and contemporary repertoire and his extensive teaching career in Europe.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d886d15af4819092f92f8a129763e6 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3f2db20d48190b5d69ccf89f3bc42 |
completed | April 18, 2026, 9:08 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a014158ed8c8190adb3c03c8a114a59 |
completed | May 11, 2026, 2:39 a.m. |
Created at: April 10, 2026, 5:36 a.m.