Triple
T29031138
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chung Hua University |
E737727
|
entity |
| Predicate | hasPrimaryDisciplineGroup |
P134380
|
FINISHED |
| Object | STEM |
—
|
NE NERFINISHED |
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: STEM | Statement: [Chung Hua University, hasPrimaryDisciplineGroup, STEM]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPrimaryDisciplineGroup Context triple: [Chung Hua University, hasPrimaryDisciplineGroup, STEM]
-
A.
hasPrimaryDisciplineStructure
Indicates that an entity is associated with its main or principal organizational or structural form of discipline.
-
B.
disciplineGroupOf
chosen
Indicates that one entity is a discipline group to which another entity (such as a person, course, or activity) belongs or is associated.
-
C.
hasSubdiscipline
Indicates that one discipline includes another, more specialized field of study as a subordinate branch.
-
D.
hasDisciplineRole
Indicates that an entity holds a specific role or function within a particular discipline or field.
-
E.
hasPrimarySubject
Indicates that an entity is the main or principal subject associated with another entity or resource.
- 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_69f077ef00fc81909325f084ad37c035 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69ff32b88bf48190b45afd1b60cb511c |
completed | May 9, 2026, 1:12 p.m. |
| PD | Predicate disambiguation | batch_69ff3031e18881908927b2ab452de863 |
completed | May 9, 2026, 1:01 p.m. |
Created at: April 28, 2026, 9:55 a.m.