Triple
T10700659
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harish-Chandra Research Institute |
E252266
|
entity |
| Predicate | hasAcademicProgramme |
P1718
|
FINISHED |
| Object | PhD programme in mathematics |
—
|
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: PhD programme in mathematics | Statement: [Harish-Chandra Research Institute, hasAcademicProgramme, PhD programme in mathematics]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAcademicProgramme Context triple: [Harish-Chandra Research Institute, hasAcademicProgramme, PhD programme in mathematics]
-
A.
hasAcademicProgramsWith
Indicates that two institutions or entities offer or participate in the same or jointly organized academic programs.
-
B.
hasEducationalProgram
Indicates that an entity offers, runs, or is associated with a specific educational program.
-
C.
hasMajorProgram
Indicates that an educational institution offers a specific field of study as a primary academic program.
-
D.
hasUndergraduatePrograms
Indicates that an educational institution offers one or more undergraduate-level academic programs.
-
E.
hasDoctoralProgram
chosen
Indicates that an institution or academic unit offers and administers a doctoral-level degree program.
- 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_69d6aa5cbabc8190973e683950d89faf |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d6fd8bb7408190a350840e1df3b910 |
completed | April 9, 2026, 1:14 a.m. |
| PD | Predicate disambiguation | batch_69d6dd8cc0788190b4c02a772e4b58b3 |
completed | April 8, 2026, 10:58 p.m. |
Created at: April 8, 2026, 9:12 p.m.