Triple
T7524096
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ma Su |
E177846
|
entity |
| Predicate | teacherStudentRelationship |
P18487
|
FINISHED |
| Object | disciple of Zhuge Liang |
—
|
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: disciple of Zhuge Liang | Statement: [Ma Su, teacherStudentRelationship, disciple of Zhuge Liang]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: teacherStudentRelationship Context triple: [Ma Su, teacherStudentRelationship, disciple of Zhuge Liang]
-
A.
notableStudentOrMentorRelationship
chosen
Indicates a notable educational or mentorship relationship between two individuals, where one has been a significant student or mentor of the other.
-
B.
hasStudents
Indicates that an entity (such as a class, school, or teacher) is associated with one or more students.
-
C.
teacherOrInfluence
Indicates that one entity serves as a teacher to, or has a significant influence on the development, behavior, or thinking of, another entity.
-
D.
hasTeacher
Indicates that one entity serves as an instructor or educator for another entity.
-
E.
notableStudentOrSubordinate
Indicates that one entity is a notable student or subordinate of another entity, highlighting a significant mentorship or hierarchical relationship between them.
- 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_69c69f29bf3081909a146aec7755f185 |
completed | March 27, 2026, 3:15 p.m. |
| NER | Named-entity recognition | batch_69c6f7c61b508190b582f54ecbb387e3 |
completed | March 27, 2026, 9:33 p.m. |
| PD | Predicate disambiguation | batch_69c6f4d6bb808190bdd04499fd3bceb6 |
completed | March 27, 2026, 9:21 p.m. |
Created at: March 27, 2026, 3:46 p.m.