Triple
T23926670
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Department of English, Daulat Ram College |
E602373
|
entity |
| Predicate | mediumOfStudy |
P12427
|
FINISHED |
| Object | English |
—
|
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: English | Statement: [Department of English, Daulat Ram College, mediumOfStudy, English]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mediumOfStudy Context triple: [Department of English, Daulat Ram College, mediumOfStudy, English]
-
A.
mediumOfInstruction
chosen
Indicates that a particular language or medium is used as the primary means of instruction or teaching in an educational context.
-
B.
partOfStudy
Indicates that something is a component, segment, or subset within a larger study or research project.
-
C.
studType
Indicates a relationship where an entity is classified as a particular type or category of stud (e.g., a specific kind of fastener or structural element).
-
D.
collegeMajor
Indicates that a person’s primary field of academic study at a college or university is a specified subject or discipline.
-
E.
hasSubjectOfStudy
Indicates that an entity (such as a person or organization) focuses on, researches, or specializes in a particular field or topic of study.
- 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_69e2953b928c819095395fa87baca583 |
completed | April 17, 2026, 8:16 p.m. |
| NER | Named-entity recognition | batch_69f1cf1e13e8819096432b8133c7d71e |
completed | April 29, 2026, 9:27 a.m. |
| PD | Predicate disambiguation | batch_69f16151ebdc819086e9e1d7cc1f4f3c |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:47 p.m.