Triple
T10722093
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Charles Bronson |
E252845
|
entity |
| Predicate | workedWith |
P398
|
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: [Charles Bronson, workedWith, Michael Winner]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Winner Context triple: [Charles Bronson, workedWith, 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.
Gered Mankowitz
Gered Mankowitz is a British photographer best known for his iconic music and rock-and-roll imagery, including portraits and album covers for major artists.
-
C.
Lew Grade
Lew Grade was a prominent British media mogul and television producer who played a key role in shaping commercial television in the UK during the mid-20th century.
-
D.
Ronald Neame
Ronald Neame was a British film director, producer, and cinematographer known for works such as "The Poseidon Adventure" and collaborations with Alec Guinness.
-
E.
Michael Aldrich
Michael Aldrich was a British inventor and entrepreneur best known for pioneering online shopping and developing one of the first systems to connect consumers to businesses via a domestic television and telephone line.
- 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_69d6aa5d8be481909a43218b2bfdbe95 |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d70d43655081909b071100c96cb4f6 |
completed | April 9, 2026, 2:21 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69dbb738f8488190837a675b82ce75aa |
completed | April 12, 2026, 3:16 p.m. |
Created at: April 8, 2026, 9:13 p.m.