Triple
T35421542
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Donut Secret 1 |
E1023807
|
entity |
| Predicate | savePointAccessible |
P22633
|
FINISHED |
| Object | indirectly via connected levels |
—
|
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: indirectly via connected levels | Statement: [Donut Secret 1, savePointAccessible, indirectly via connected levels]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: savePointAccessible Context triple: [Donut Secret 1, savePointAccessible, indirectly via connected levels]
-
A.
areAccessibleAt
chosen
Indicates that certain entities can be reached, used, or entered at a specified location, time, or context.
-
B.
saveBy
Indicates that one entity preserves, rescues, or protects another entity from loss, harm, or danger.
-
C.
reserveLocation
Indicates that an entity designates or sets aside a specific place for a particular use, purpose, or future activity.
-
D.
savedWith
Indicates that one entity is preserved, stored, or kept together in association with another entity.
-
E.
startPoint
Indicates the initial location or position from which an object, path, or action begins.
- 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_69f76df6704081909900c60be10d5849 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7958d59388190a937ac6f4c81d3c9 |
completed | May 3, 2026, 6:35 p.m. |
| PD | Predicate disambiguation | batch_69f7910770108190bdd39ddb5d304f54 |
completed | May 3, 2026, 6:16 p.m. |
Created at: May 3, 2026, 4:03 p.m.