Triple
T2926710
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paddington 2 |
E78861
|
entity |
| Predicate | writer |
P1360
|
FINISHED |
| Object | Paul King |
E311062
|
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: Paul King | Statement: [Paddington 2, writer, Paul King]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paul King Context triple: [Paddington 2, writer, Paul King]
-
A.
Paul King
chosen
Paul King is a British filmmaker and screenwriter best known for directing the critically acclaimed Paddington films.
-
B.
Phil Lord
Phil Lord is an American filmmaker, writer, and producer best known for his inventive, comedic work on projects like The Lego Movie and the 21 Jump Street and Spider-Verse films.
-
C.
Michael Arndt
Michael Arndt is an Academy Award–winning American screenwriter known for acclaimed films such as Little Miss Sunshine and Toy Story 3.
-
D.
Jordan Vogt-Roberts
Jordan Vogt-Roberts is an American film director best known for helming the 2017 blockbuster monster movie "Kong: Skull Island."
-
E.
Peter Hedges
Peter Hedges is an American novelist, playwright, and filmmaker best known for writing the novel and screenplay for "What's Eating Gilbert Grape" and directing films such as "Pieces of April" and "Dan in Real Life."
- 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_69ad8b0d40b481908bc2a5fa2e73c3fb |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad97c1e9c08190bcec80bc3262697a |
completed | March 8, 2026, 3:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b0fc632afc819098021312c748346b |
completed | March 11, 2026, 5:23 a.m. |
Created at: March 8, 2026, 2:55 p.m.