Triple
T6970464
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Indian Institute of Technology Guwahati |
E161585
|
entity |
| Predicate | academicStart |
P55233
|
FINISHED |
| Object | 1995 |
—
|
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: 1995 | Statement: [Indian Institute of Technology Guwahati, academicStart, 1995]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: academicStart Context triple: [Indian Institute of Technology Guwahati, academicStart, 1995]
-
A.
educationStartTime
chosen
Indicates the point in time when an educational activity, program, or enrollment for an entity begins.
-
B.
academicSelection
Indicates a relationship where an entity chooses or designates another entity for an academic purpose, role, or opportunity.
-
C.
academicCalendar
Indicates the schedule or structure of academic terms, sessions, and key dates associated with an educational institution or program.
-
D.
academicAdvisor
Indicates that one entity serves as the academic advisor, providing formal guidance and oversight on academic matters, to another entity.
-
E.
academicYearType
Indicates the classification of an academic year according to its structural or administrative type (e.g., semester-based, quarter-based, fiscal year, etc.).
- 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_69c68854a0d88190bc0bf82263f1afce |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6db1649288190a52c7dab57b3c7dc |
completed | March 27, 2026, 7:31 p.m. |
| PD | Predicate disambiguation | batch_69c6d7c262508190a7708b3d9cf23d7c |
completed | March 27, 2026, 7:17 p.m. |
Created at: March 27, 2026, 2:30 p.m.