Triple
T36146263
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dragon Pictures |
E1045459
|
entity |
| Predicate | associatedWithFilmWriter |
P33118
|
FINISHED |
| Object | Frank Cottrell Boyce |
E62133
|
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: Frank Cottrell Boyce | Statement: [Dragon Pictures, associatedWithFilmWriter, Frank Cottrell Boyce]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedWithFilmWriter Context triple: [Dragon Pictures, associatedWithFilmWriter, Frank Cottrell Boyce]
-
A.
associatedWithScreenwriter
chosen
Indicates a relationship in which an entity is connected or linked to a screenwriter, typically through collaboration, authorship, or professional involvement in a screenwriting context.
-
B.
associatedWithComposerOfFilm
Indicates a relationship where an entity is connected to the composer who created the musical score for a specific film.
-
C.
filmWriterOfWorkAppearedIn
Indicates that a person is the writer of a film in which they themselves also appeared (e.g., as an actor or on-screen participant).
-
D.
associatedWithProducerOfFilm
Indicates that one entity has an association or connection with the producer of a particular film.
-
E.
screenwriterWorkedWith
Indicates that a screenwriter has collaborated professionally with another individual on one or more film, television, or related media projects.
- F. None of above.
Provenance (4 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_69f76e37ace88190a906b107d388f5d1 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a037c8d06cc8190ab6a5e18d9d2571e |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a39e6c0c56481909ecfbe55f1e6ffaa |
completed | June 23, 2026, 1:52 a.m. |
| PD | Predicate disambiguation | batch_6a037a0895b48190acdd88dc10db7be7 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:08 p.m.