Triple
T21742611
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Buddy Films |
E536698
|
entity |
| Predicate | primaryAnimalStar |
P42281
|
FINISHED |
| Object | golden retriever |
—
|
LITERAL 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: golden retriever | Statement: [Buddy Films, primaryAnimalStar, golden retriever]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryAnimalStar Context triple: [Buddy Films, primaryAnimalStar, golden retriever]
-
A.
sourceAnimal
Indicates that one entity is the animal from which another entity (such as a product, material, or sample) is derived or obtained.
-
B.
animalProtagonist
Indicates that the main character or central figure in a narrative is an animal.
-
C.
featuresAnimalsFrom
Indicates that one entity includes, presents, or showcases animals originating from or associated with another entity.
-
D.
animalTypeFeatured
chosen
Indicates that a particular type or category of animal is highlighted or prominently showcased in a given context.
-
E.
animalClassFeatured
Indicates that a particular animal class is highlighted or prominently presented in relation to something (such as content, a display, or a context).
- F. None of above.
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_69e0c46df5448190b4322127ffc4c690 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f01a7322348190b2145fa922c480ed |
completed | April 28, 2026, 2:24 a.m. |
| PD | Predicate disambiguation | batch_69e6969c16fc8190b5126c169317d85d |
completed | April 20, 2026, 9:11 p.m. |
Created at: April 16, 2026, 6:49 p.m.