Triple
T26947689
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dorothy is shipwrecked on her way to Australia |
E678690
|
entity |
| Predicate | causesSeparationFrom |
P168932
|
FINISHED |
| Object | Uncle Henry |
—
|
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: Uncle Henry | Statement: [Dorothy is shipwrecked on her way to Australia, causesSeparationFrom, Uncle Henry]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: causesSeparationFrom Context triple: [Dorothy is shipwrecked on her way to Australia, causesSeparationFrom, Uncle Henry]
-
A.
typeOfSeparation
Indicates the specific manner or category of separation that exists or occurred between entities.
-
B.
createdBySeparationFrom
Indicates that one entity comes into existence as a result of being separated or split off from another entity.
-
C.
wouldHaveBeenSeparatedFrom
Indicates a hypothetical or counterfactual situation in which one entity would have been divided, detached, or kept apart from another entity if certain conditions had occurred.
-
D.
laterSeparatedFrom
Indicates that one entity became separated from another at a later time than some referenced separation event.
-
E.
separates
Indicates that one entity divides, parts, or keeps other entities apart from each other.
- F. None of above. chosen
Provenance (4 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_69eeeb4d69588190a7c912164a1c37b3 |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69f67866e9248190b7ba218f9ca2ae8d |
completed | May 2, 2026, 10:19 p.m. |
| PD | Predicate disambiguation | batch_69f675fd59608190b246383435e68fce |
completed | May 2, 2026, 10:09 p.m. |
| PDg | Predicate description generation | batch_69f676c35f3481909b9ba18a5662d6ce |
completed | May 2, 2026, 10:12 p.m. |
Created at: April 27, 2026, 6:22 a.m.