Triple
T2438482
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dublin City University |
E53217
|
entity |
| Predicate | hasSpecialFocus |
P34683
|
FINISHED |
| Object | work placement and internships |
—
|
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: work placement and internships | Statement: [Dublin City University, hasSpecialFocus, work placement and internships]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSpecialFocus Context triple: [Dublin City University, hasSpecialFocus, work placement and internships]
-
A.
hasSpecial
Indicates that an entity possesses or is associated with a distinctive or exceptional attribute, status, or feature compared to others.
-
B.
hasProgramFocus
chosen
Indicates that an entity (such as a program or initiative) is oriented around or primarily concerned with a particular thematic area, topic, or objective.
-
C.
hasPrimaryFocus
Indicates that something is the main subject, concern, or area of attention for an entity or activity.
-
D.
hasSpecialCategory
Indicates that an entity is associated with a designated special or exceptional category distinct from its standard classifications.
-
E.
hasSpecials
Indicates that an entity offers or is associated with special deals, promotions, or limited-time offers.
- 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_69ab495b6dac8190ac82661aa1452222 |
completed | March 6, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69abcebf7cac8190889e6890d72c256c |
completed | March 7, 2026, 7:07 a.m. |
| PD | Predicate disambiguation | batch_69abc5ac11b081908ce6a506e81a742a |
completed | March 7, 2026, 6:29 a.m. |
Created at: March 6, 2026, 9:43 p.m.