Triple
T18451149
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Savitri |
E450783
|
entity |
| Predicate | hasTypeOfStory |
P121234
|
FINISHED |
| Object | didactic tale |
—
|
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: didactic tale | Statement: [Savitri, hasTypeOfStory, didactic tale]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTypeOfStory Context triple: [Savitri, hasTypeOfStory, didactic tale]
-
A.
hasStorylineType
chosen
Indicates that an entity’s storyline belongs to or is categorized under a specific type or narrative classification.
-
B.
hasStaffTypeInStory
Indicates that a story involves or is associated with a particular type or category of staff.
-
C.
hasFolkTaleType
Indicates that an entity (such as a story) is classified as belonging to a particular folk tale type or category.
-
D.
hasVariantStoriesIn
Indicates that an entity has alternative or differing narrative versions that occur or are found within a specified context or source.
-
E.
hasStoryPath
Indicates that there exists a defined narrative route or sequence of events connecting one entity to another within a story or interactive experience.
- 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_69d8d38345688190b565eac2e4cd7935 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e52648476c8190a5d8c3297d836f62 |
completed | April 19, 2026, 7 p.m. |
| PD | Predicate disambiguation | batch_69e469d05cf4819099baf1665a9cf18a |
completed | April 19, 2026, 5:36 a.m. |
Created at: April 10, 2026, 11:31 a.m.