Triple
T21587310
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Agatha |
E532683
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object | Michael Apted |
—
|
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: Michael Apted | Statement: [Agatha, director, Michael Apted]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Apted Context triple: [Agatha, director, Michael Apted]
-
A.
Michael Apted
chosen
Michael Apted was a British film director and documentarian best known for the long-running "Up" documentary series and feature films such as "Gorillas in the Mist" and "The World Is Not Enough."
-
B.
Charles Ferguson
Charles Ferguson is a fictional intelligence operative and central protagonist in Jack Higgins’s thriller novels.
-
C.
Bryan Forbes
Bryan Forbes was a British film director, screenwriter, and actor known for works such as "The Stepford Wives" and "Whistle Down the Wind."
-
D.
Simon Gavron
Simon Gavron is the father of British-American actor Rafi Gavron.
-
E.
Stephen Daldry
Stephen Daldry is an acclaimed British theatre and film director and producer known for works such as "Billy Elliot," "The Hours," and "The Reader."
- 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_69e0c46251648190876f0427cf2d321b |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69eeeb621ab88190a33a943424ffb306 |
completed | April 27, 2026, 4:51 a.m. |
Created at: April 16, 2026, 6:31 p.m.