Triple
T35778072
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Emser pastilles |
E1034352
|
entity |
| Predicate | isDissolved |
P183659
|
FINISHED |
| Object | slowly in the mouth |
—
|
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: slowly in the mouth | Statement: [Emser pastilles, isDissolved, slowly in the mouth]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isDissolved Context triple: [Emser pastilles, isDissolved, slowly in the mouth]
-
A.
isDissolvedBy
Indicates that one substance causes another substance to break down and go into solution.
-
B.
dissolvedStatus
Indicates that an entity’s prior state, structure, or formal existence has been terminated or brought to an end.
-
C.
dissolvedWhen
Indicates that one entity ceases to exist, function, or remain intact at the time or under the conditions specified by another entity or event.
-
D.
hasDissolutionDate
Indicates the date on which an entity, such as an organization or legal arrangement, formally ceases to exist or is officially dissolved.
-
E.
dissolvedBefore
Indicates that one entity ceased to exist, function, or remain in solution at an earlier time than another entity.
- 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_69f76e14a1e081908eddd57bd6fdb3be |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7a1fd19a88190968cb8775212e3ac |
completed | May 3, 2026, 7:29 p.m. |
| PD | Predicate disambiguation | batch_69f7a070e23881909a233370acb57384 |
completed | May 3, 2026, 7:22 p.m. |
| PDg | Predicate description generation | batch_69f7a162672481909773f8383d91159a |
completed | May 3, 2026, 7:26 p.m. |
Created at: May 3, 2026, 4:06 p.m.