Triple
T28520492
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fall from Innocence |
E721748
|
entity |
| Predicate | includedInCollectionWith |
P56991
|
FINISHED |
| Object | Rita Hayworth and Shawshank Redemption |
—
|
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: Rita Hayworth and Shawshank Redemption | Statement: [Fall from Innocence, includedInCollectionWith, Rita Hayworth and Shawshank Redemption]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: includedInCollectionWith Context triple: [Fall from Innocence, includedInCollectionWith, Rita Hayworth and Shawshank Redemption]
-
A.
includedInCollectionAbout
Indicates that an item is part of, or contained within, a collection whose organizing theme or subject is about a specified entity or topic.
-
B.
includedInCollectionType
Indicates that one entity is a member or component of a specified collection type.
-
C.
collectionAlsoIncludes
Indicates that a collection contains, in addition to some already-specified items, one or more further items that are also part of that same collection.
-
D.
includedBy
chosen
Indicates that one entity is contained within, encompassed by, or treated as a subset or member of another entity.
-
E.
displayedInCollection
Indicates that an item is or was shown as part of a particular collection or exhibition grouping.
- 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_69f01a5cbcc4819083fb4e723378713e |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_69ff0e9c75208190a4423261f00b79b3 |
completed | May 9, 2026, 10:38 a.m. |
| PD | Predicate disambiguation | batch_69ff0e07f08481909c4ae322632a6bf0 |
completed | May 9, 2026, 10:35 a.m. |
Created at: April 28, 2026, 3:20 a.m.