Triple
T13541585
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jan de Bont |
E323397
|
entity |
| Predicate | cinematographyFor |
P90619
|
FINISHED |
| Object | Cujo |
E507765
|
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: Cujo | Statement: [Jan de Bont, cinematographyFor, Cujo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cujo Context triple: [Jan de Bont, cinematographyFor, Cujo]
-
A.
Cujo
chosen
Cujo is a horror novel by Stephen King about a rabid dog terrorizing a small-town family.
-
B.
The Dog
The Dog is a nickname for Earl Simmons, better known as the influential American rapper and actor DMX.
-
C.
The Dog
The Dog is the witty, talking canine companion and narrator’s sidekick in Jim Henson’s fantasy television series *The Storyteller*.
-
D.
The Dog
The Dog is a haunting and enigmatic painting by Francisco Goya, notable for its stark composition and sense of isolation, and is one of his renowned Black Paintings.
-
E.
The Dog Pound
The Dog Pound is the passionate student cheering section known for creating an energetic home-ice atmosphere at Boston University Terriers men's hockey games.
- 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_69d8076776248190bdf0d4fa1f85a5fc |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbbe99ddc08190a8d79107c8e176fa |
completed | April 12, 2026, 3:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f75d9eaff881909a3cd9e88bb4ec5e |
completed | May 3, 2026, 2:37 p.m. |
Created at: April 9, 2026, 9:45 p.m.