Triple
T10140208
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ron Saunders |
E226961
|
entity |
| Predicate | fullName |
P16
|
FINISHED |
| Object | Ronald Saunders |
E226961
|
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: Ronald Saunders | Statement: [Ron Saunders, fullName, Ronald Saunders]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ronald Saunders Context triple: [Ron Saunders, fullName, Ronald Saunders]
-
A.
Ronald Adam
Ronald Adam was a British actor and Royal Air Force officer known for his character roles in mid-20th-century films and stage productions.
-
B.
Ron Saunders
chosen
Ron Saunders was an English football manager best known for leading Aston Villa to major domestic success, including the First Division title in 1980–81.
-
C.
Ronald Bailey
Ronald Bailey is a family member of Pro Football Hall of Fame cornerback Champ Bailey.
-
D.
Rod Liddle
Rod Liddle is a British journalist and commentator known for his provocative columns and outspoken views on politics and culture.
-
E.
Jeremy Saunders
Jeremy Saunders is a recurring fictional character in Satyajit Ray’s Bengali science-fiction “Professor Shonku” stories, typically appearing as an English associate in the professor’s adventurous experiments.
- 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_69ca8433ec308190b8b25a6fe359c34c |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cdeb2425008190a92c5148ed703d5c |
completed | April 2, 2026, 4:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d2e603d4548190a561e735c603946f |
completed | April 5, 2026, 10:45 p.m. |
Created at: March 30, 2026, 9:07 p.m.