Triple
T20492572
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Modesty Blaise |
E502781
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Evan Jones |
—
|
NE NERFINISHED |
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: Evan Jones | Statement: [Modesty Blaise, screenwriter, Evan Jones]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Evan Jones Context triple: [Modesty Blaise, screenwriter, Evan Jones]
-
A.
Evan Jones
Evan Jones is an American character actor known for his supporting roles in films such as "Den of Thieves," "8 Mile," and "Jarhead."
-
B.
Evan Jones
chosen
Evan Jones is a Jamaican-born British screenwriter known for his work on socially conscious films and television dramas in the mid-20th century.
-
C.
Evan Harris
Evan Harris is a British Liberal Democrat politician and former Member of Parliament known for his advocacy on civil liberties, science, and secularism.
-
D.
Joel Eaves
Joel Eaves was an American college basketball coach best known for leading Auburn University’s men’s basketball program to national prominence in the mid-20th century.
-
E.
Evan Buckley
Evan Buckley is a central firefighter character on the television drama "9-1-1," known for his bravery, impulsive nature, and emotionally driven storylines.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4b0373881909dd3e9387f82eab4 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e69cbb3bd081909351525208b41bba |
completed | April 20, 2026, 9:38 p.m. |
Created at: April 16, 2026, 11:35 a.m.