Triple
T12115791
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BBC Radio Sherlock Holmes series |
E288557
|
entity |
| Predicate | stars |
P1956
|
FINISHED |
| Object | Andrew Sachs |
E417860
|
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: Andrew Sachs | Statement: [BBC Radio Sherlock Holmes series, stars, Andrew Sachs]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Andrew Sachs Context triple: [BBC Radio Sherlock Holmes series, stars, Andrew Sachs]
-
A.
Andrew Sachs
chosen
Andrew Sachs was a British actor best known for his comedic role as the hapless waiter Manuel in the classic sitcom "Fawlty Towers."
-
B.
Clifford Stein
Clifford Stein is a computer scientist and professor best known for his contributions to algorithms and operations research, including co-authoring the widely used textbook "Introduction to Algorithms."
-
C.
Teddy Schwarzman
Teddy Schwarzman is an American film producer and founder of Black Bear Pictures, known for backing acclaimed films such as "The Imitation Game."
-
D.
Andrew Saks
Andrew Saks was an American businessman and retailer best known as the founder of the luxury department store Saks Fifth Avenue.
-
E.
William Margulies
William Margulies was an American cinematographer known for his work on mid-20th-century Hollywood films and television productions.
- 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_69d6ab4a5c448190a110d1273314b21a |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d9156921dc8190aa132b0ab3a7c184 |
completed | April 10, 2026, 3:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f5f67f9c30819089305d5d42210c34 |
completed | May 2, 2026, 1:05 p.m. |
Created at: April 8, 2026, 9:49 p.m.