Triple
T16676366
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Horses |
E405223
|
entity |
| Predicate | featuresMusician |
P20942
|
FINISHED |
| Object | Richard Sohl |
E958869
|
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: Richard Sohl | Statement: [Horses, featuresMusician, Richard Sohl]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Richard Sohl Context triple: [Horses, featuresMusician, Richard Sohl]
-
A.
Richard Sohl
chosen
Richard Sohl was an American pianist and keyboardist best known for his work with the Patti Smith Group and other influential punk and rock acts of the 1970s and 1980s.
-
B.
Richard Seifert
Richard Seifert was a prominent 20th-century British architect known for his influential and often controversial modernist high-rise buildings across London.
-
C.
Mark Kohr
Mark Kohr is an American music video director known for his work with prominent alternative rock bands in the 1990s.
-
D.
Richard Schayer
Richard Schayer was an American screenwriter prominent during the silent and early sound eras of Hollywood, contributing to numerous films across various genres.
-
E.
Richard Plepler
Richard Plepler is an American media executive best known for his tenure as CEO of HBO, where he oversaw the development of numerous acclaimed television series.
- 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_69d8838c28748190b3f5967c743940ab |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e37d6b69cc8190b19632e1b4293569 |
completed | April 18, 2026, 12:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00c29693dc819096993d8ba0fb3d71 |
completed | May 10, 2026, 5:38 p.m. |
Created at: April 10, 2026, 5:19 a.m.