Triple
T7918080
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bee Movie |
E183876
|
entity |
| Predicate | storyBy |
P1955
|
FINISHED |
| Object | Andy Robin |
E700249
|
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: Andy Robin | Statement: [Bee Movie, storyBy, Andy Robin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Andy Robin Context triple: [Bee Movie, storyBy, Andy Robin]
-
A.
Andy Robin
chosen
Andy Robin is a screenwriter best known for co-writing the animated comedy film "Bee Movie."
-
B.
Alain Attal
Alain Attal is a French film producer known for his work on numerous acclaimed contemporary French movies.
-
C.
Olivier Nakache
Olivier Nakache is a French film director and screenwriter best known for co-directing the internationally acclaimed comedy-drama "The Intouchables."
-
D.
Philippe Quentin
Philippe Quentin is a distinguished physicist recognized for his significant contributions to nuclear physics, honored as a laureate of the prestigious Lise Meitner Prize.
-
E.
Michel Robin
Michel Robin was a French character actor known for his extensive work in film, television, and theater, often appearing in historical and dramatic roles.
- 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_69ca828efbe48190bd48482650182e79 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb3a8fbbb48190b50def4941761a31 |
completed | March 31, 2026, 3:07 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cbdffe21fc8190acffc2e92d13aa5d |
completed | March 31, 2026, 2:53 p.m. |
Created at: March 30, 2026, 5:05 p.m.