Triple
T2793857
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marie Skłodowska‑Curie Actions |
E61989
|
entity |
| Predicate | supportsCareerStage |
P43181
|
FINISHED |
| Object | doctoral researchers |
—
|
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: doctoral researchers | Statement: [Marie Skłodowska‑Curie Actions, supportsCareerStage, doctoral researchers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsCareerStage Context triple: [Marie Skłodowska‑Curie Actions, supportsCareerStage, doctoral researchers]
-
A.
isStageInCareerOf
Indicates that one entity represents a particular phase or stage within the professional career of another entity.
-
B.
managedCareerOf
Indicates that one entity was responsible for overseeing, directing, or handling the professional career of another entity.
-
C.
partOfCareer
Indicates that one entity represents a role, position, or period that forms a component or phase within another entity’s overall career.
-
D.
targetCareer
Indicates that one entity is the intended or pursued career or professional goal of another entity.
-
E.
laterCareer
Indicates that the associated information or events pertain to a later stage or phase in an entity’s professional life or career trajectory.
- F. None of above. chosen
Provenance (4 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_69ab4b7f51d881908768300ebd2fbdae |
completed | March 6, 2026, 9:47 p.m. |
| NER | Named-entity recognition | batch_69abddd33610819085ac7c5bec0e6af0 |
completed | March 7, 2026, 8:12 a.m. |
| PD | Predicate disambiguation | batch_69abdd040f9481908e9c7a2df88ea1ae |
completed | March 7, 2026, 8:08 a.m. |
| PDg | Predicate description generation | batch_69abddcc348081908b5f760899389d4f |
completed | March 7, 2026, 8:11 a.m. |
Created at: March 6, 2026, 9:58 p.m.