Triple
T28073095
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rector of COMSATS University Islamabad |
E709458
|
entity |
| Predicate | titleUsedAt |
P173685
|
FINISHED |
| Object | COMSATS University Islamabad |
—
|
NE NERFINISHED |
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: COMSATS University Islamabad | Statement: [Rector of COMSATS University Islamabad, titleUsedAt, COMSATS University Islamabad]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: titleUsedAt Context triple: [Rector of COMSATS University Islamabad, titleUsedAt, COMSATS University Islamabad]
-
A.
titleUsedSince
Indicates that a particular title has been in use starting from a specified point in time.
-
B.
titleUsage
Indicates how a title is applied, referenced, or used in relation to an entity or context.
-
C.
usedAsTitleUntil
Indicates that a particular title was held or used by an entity up to (and including or until) a specified end time.
-
D.
usedAsTitleOn
chosen
Indicates that something functions as a title applied to or displayed on a particular entity.
-
E.
usedTitleIn
Indicates that one entity employed or referenced another entity as a title in some context.
- 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_69ef9b6f8078819098b741274cd1a2ee |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69fce28d6c3081908bf76f5db63ecf68 |
completed | May 7, 2026, 7:05 p.m. |
| PD | Predicate disambiguation | batch_69fce12d2f08819082134b5eb3db6a24 |
completed | May 7, 2026, 6:59 p.m. |
Created at: April 27, 2026, 8:47 p.m.