Triple
T26525099
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Disney direct-to-video films |
E670665
|
entity |
| Predicate | exampleWork |
P33193
|
FINISHED |
| Object | The Return of Jafar |
—
|
NE NERFINISHED |
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: The Return of Jafar | Statement: [Disney direct-to-video films, exampleWork, The Return of Jafar]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: exampleWork Context triple: [Disney direct-to-video films, exampleWork, The Return of Jafar]
-
A.
workExampleOf
chosen
Indicates that something serves as an example or instance of a particular type of work or activity.
-
B.
workFor
Indicates that one entity is employed by or performs work under the authority or direction of another entity.
-
C.
workWith
Indicates that one entity collaborates or engages in work-related activities together with another entity.
-
D.
workOn
Indicates that an agent is actively engaged in performing tasks or making progress on a particular project, object, or assignment.
-
E.
showsWorkOf
Indicates that one entity presents, exhibits, or displays the work or creations produced by another entity.
- 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_69eeb31ea1e08190b9ff43cf9bc25bf8 |
completed | April 27, 2026, 12:51 a.m. |
| NER | Named-entity recognition | batch_69f6562fd3488190be1acd8c526a28d2 |
completed | May 2, 2026, 7:53 p.m. |
| PD | Predicate disambiguation | batch_69f651a731508190bb0c8c2462eba224 |
completed | May 2, 2026, 7:33 p.m. |
Created at: April 27, 2026, 1:31 a.m.