Triple
T8361621
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Button, Button |
E197019
|
entity |
| Predicate | adaptationBasisFor |
P2375
|
FINISHED |
| Object | film The Box |
—
|
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: film The Box | Statement: [Button, Button, adaptationBasisFor, film The Box]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: adaptationBasisFor Context triple: [Button, Button, adaptationBasisFor, film The Box]
-
A.
basedOnAdaptationsOf
Indicates that something is derived from or created using one or more prior adaptations of an original work, rather than directly from the original source.
-
B.
adaptationType
chosen
Indicates the specific kind or category of adaptation that relates one entity to another or to a particular context.
-
C.
adaptationBy
Indicates a relationship where one entity has been modified, transformed, or reworked by another entity into a new form or version.
-
D.
adaptationIn
Indicates that something appears, is represented, or takes place within a particular adaptation of an original work.
-
E.
adaptedTo
Indicates that one entity has been modified, adjusted, or evolved to function effectively within the conditions, requirements, or characteristics defined 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_69ca82f2dbe48190aba982e75a0d94de |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb8074e4588190b394d1622adca2cb |
completed | March 31, 2026, 8:06 a.m. |
| PD | Predicate disambiguation | batch_69cb70ca25548190b0f90c5384e3fb3c |
completed | March 31, 2026, 6:59 a.m. |
Created at: March 30, 2026, 6 p.m.