Triple
T6198652
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | College of Liberal Arts at Temple University |
E138573
|
entity |
| Predicate | focusesOnSkill |
P45342
|
FINISHED |
| Object | writing |
—
|
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: writing | Statement: [College of Liberal Arts at Temple University, focusesOnSkill, writing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: focusesOnSkill Context triple: [College of Liberal Arts at Temple University, focusesOnSkill, writing]
-
A.
skillEmphasis
chosen
Indicates that a particular skill is given special focus, priority, or importance within a context such as a role, task, or curriculum.
-
B.
focusesOn
Indicates that one entity directs its attention, effort, or primary activity toward another entity or specific subject.
-
C.
skillSet
Indicates that an entity possesses or is associated with a particular collection of skills or competencies.
-
D.
skillAssessed
Indicates that an entity’s skill or competency has been evaluated or measured, typically by another agent or process.
-
E.
kills
Indicates that one entity causes the death of another entity, ending its life.
- 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_69c008ab9b3081908a11b2c744838435 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c06251b47881909bd8d2ea37541959 |
completed | March 22, 2026, 9:42 p.m. |
| PD | Predicate disambiguation | batch_69c055fbce1081908805fd12e242ab96 |
completed | March 22, 2026, 8:50 p.m. |
Created at: March 22, 2026, 4:20 p.m.