Triple
T3859986
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Sentinel |
E90110
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object | Michael Winner |
E167698
|
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: Michael Winner | Statement: [The Sentinel, director, Michael Winner]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Winner Context triple: [The Sentinel, director, Michael Winner]
-
A.
Michael Winner
chosen
Michael Winner was a British film director and producer best known for directing the "Death Wish" series starring Charles Bronson.
-
B.
Tony Richardson
Tony Richardson was a British film and theatre director associated with the Free Cinema movement and known for influential works such as "Tom Jones" and "The Loneliness of the Long Distance Runner."
-
C.
Joe Eszterhas
Joe Eszterhas is a Hungarian-American screenwriter best known for his provocative, high-profile Hollywood thrillers of the late 20th century.
-
D.
Mark Robson
Mark Robson was a Canadian-born film editor-turned-director known for his work in Hollywood on acclaimed films from the 1940s through the 1960s.
-
E.
Bruce Gilliat
Bruce Gilliat is an internet entrepreneur best known as the co-founder of Alexa Internet, a pioneering web traffic analysis and ranking service.
- 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_69aed95b3c088190a8f85d19e6070599 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeec1ff39c8190b83a88abd840a0e3 |
completed | March 9, 2026, 3:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b512348fe88190b5ae942809732b76 |
completed | March 14, 2026, 7:45 a.m. |
Created at: March 9, 2026, 3:19 p.m.