Triple
T2487
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Osaka Imperial University |
E46
|
entity |
| Predicate | researchFocus |
P31
|
FINISHED |
| Object | fundamental science |
—
|
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: fundamental science | Statement: [Osaka Imperial University, researchFocus, fundamental science]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: researchFocus Context triple: [Osaka Imperial University, researchFocus, fundamental science]
-
A.
fieldOfWork
Indicates the professional or academic domain in which an entity is primarily engaged or specializes.
-
B.
focusesOn
chosen
Indicates that one entity directs its attention, effort, or primary activity toward another entity or specific subject.
-
C.
academicAdvisor
Indicates that one entity serves as the academic advisor, providing formal guidance and oversight on academic matters, to another entity.
-
D.
focusPeriod
Indicates the specific time span during which attention, activity, or analysis is concentrated on something.
-
E.
publicationType
Indicates the specific category or format of a published work that characterizes how it is issued or presented.
- 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_69a22cde80848190b62c5f556b4d62ba |
completed | Feb. 27, 2026, 11:46 p.m. |
| NER | Named-entity recognition | batch_69a2346846608190b6b40d31f1dbd685 |
completed | Feb. 28, 2026, 12:18 a.m. |
| PD | Predicate disambiguation | batch_69a233c396ec8190986608d07fb251d4 |
completed | Feb. 28, 2026, 12:16 a.m. |
Created at: Feb. 27, 2026, 11:48 p.m.