Triple
T3162756
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Tweed |
E66139
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | John Tweed |
E66139
|
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: John Tweed | Statement: [John Tweed, name, John Tweed]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Tweed Context triple: [John Tweed, name, John Tweed]
-
A.
John Tweed
chosen
John Tweed was a British sculptor known for creating prominent public monuments and statues in the early 20th century.
-
B.
Ian Sharp
Ian Sharp is a British film and television director known for his work on action-driven projects, including sequences in the James Bond film "GoldenEye."
-
C.
John Bullough
John Bullough was a British industrialist from a prominent Lancashire textile family, known for his involvement in the cotton machinery industry and substantial wealth in the 19th century.
-
D.
Charles McNaughton
Charles McNaughton was a British actor active in the early 20th century, known for his character roles in films and on stage.
-
E.
James Duff
James Duff is an American television writer and producer best known for creating the crime drama series "The Closer."
- 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_69ad85850c1481908a9e9c6242238de2 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada61a4b8481908897a8d39d94c2f4 |
completed | March 8, 2026, 4:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b235d07ad88190838a845b5ade05a0 |
completed | March 12, 2026, 3:41 a.m. |
Created at: March 8, 2026, 3:06 p.m.