Triple
T23256844
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Poro society |
E581896
|
entity |
| Predicate | initiationSetting |
P138795
|
FINISHED |
| Object | bush schools |
—
|
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: bush schools | Statement: [Poro society, initiationSetting, bush schools]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: initiationSetting Context triple: [Poro society, initiationSetting, bush schools]
-
A.
initiationFeature
Indicates that one entity serves as a feature, mechanism, or condition that initiates, triggers, or starts an action, process, or relationship involving another entity.
-
B.
initiationPractice
Indicates the act of beginning, launching, or formally starting a particular practice, process, or activity.
-
C.
initiationStatus
Indicates the current state or phase of beginning or starting a process, activity, or relationship between entities.
-
D.
initiationLevels
Indicates the degree or stage at which an action, process, or relationship is begun or set in motion between entities.
-
E.
inductionSetting
chosen
Indicates the conditions or configuration under which an induction process or inductive operation is carried out.
- 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_69e246079f58819085eaa9c260906880 |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f194c4905c819099ca21c6529413ac |
completed | April 29, 2026, 5:19 a.m. |
| PD | Predicate disambiguation | batch_69effce4d704819092826931d430e8c4 |
completed | April 28, 2026, 12:18 a.m. |
Created at: April 17, 2026, 4:11 p.m.