Triple
T19530870
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ondol |
E488647
|
entity |
| Predicate | userPractice |
P10364
|
FINISHED |
| Object | sitting and sleeping on the floor |
—
|
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: sitting and sleeping on the floor | Statement: [Ondol, userPractice, sitting and sleeping on the floor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: userPractice Context triple: [Ondol, userPractice, sitting and sleeping on the floor]
-
A.
practicedWith
Indicates that one entity engaged in practice or training together with another entity.
-
B.
mentionsPractice
Indicates that one entity refers to, discusses, or brings up a particular practice in some form of communication.
-
C.
homePractice
Indicates that an activity, skill, or task is being practiced or carried out in a home setting rather than in a formal or external environment.
-
D.
practicedUnder
Indicates that one entity gained experience or training while working under the guidance, supervision, or mentorship of another entity.
-
E.
isPracticedBy
chosen
Indicates that an activity, skill, or discipline is regularly performed or carried out by a particular entity.
- 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_69d8e8db5b6c8190984b61f91981f575 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6363ec6cc8190b9e9ac0196b288f9 |
completed | April 20, 2026, 2:20 p.m. |
| PD | Predicate disambiguation | batch_69e514c9c00481909b76bda67957e58b |
completed | April 19, 2026, 5:45 p.m. |
Created at: April 10, 2026, 1:41 p.m.