Triple
T87397
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tiflis Spiritual Seminary |
E1756
|
entity |
| Predicate | subjectTaught |
P3295
|
FINISHED |
| Object | theology |
—
|
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: theology | Statement: [Tiflis Spiritual Seminary, subjectTaught, theology]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: subjectTaught Context triple: [Tiflis Spiritual Seminary, subjectTaught, theology]
-
A.
gradesTaught
Indicates the set of grade levels that a teacher or educational entity is responsible for teaching.
-
B.
hasTeachingRole
chosen
Indicates that one entity holds a position or responsibility involving teaching or instruction in relation to another entity.
-
C.
subjectMatter
Indicates the topic, theme, or content area that something (such as a work, document, or discussion) is about.
-
D.
studiedBy
Indicates that a subject (such as a field, topic, or object) is examined, researched, or learned by an agent (such as a person or group).
-
E.
isStudiedIn
Indicates that a subject (such as a topic, field, or phenomenon) is examined, researched, or learned about within a particular context, environment, or discipline.
- 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_69a24c8150408190910a693eb51c1f71 |
completed | Feb. 28, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69a2503d304c8190a0034ffa4a38a501 |
completed | Feb. 28, 2026, 2:17 a.m. |
| PD | Predicate disambiguation | batch_69a24eb6da2c8190a33d144d219f7abe |
completed | Feb. 28, 2026, 2:11 a.m. |
Created at: Feb. 28, 2026, 2:06 a.m.