Triple
T2793882
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marie Skłodowska‑Curie Actions |
E61989
|
entity |
| Predicate | supportsBeneficiaryType |
P22506
|
FINISHED |
| Object | universities |
—
|
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: universities | Statement: [Marie Skłodowska‑Curie Actions, supportsBeneficiaryType, universities]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsBeneficiaryType Context triple: [Marie Skłodowska‑Curie Actions, supportsBeneficiaryType, universities]
-
A.
beneficiaryType
chosen
Indicates the type or category of beneficiary that receives or is intended to receive the benefit or outcome of an action or resource.
-
B.
beneficiaryRequirement
Indicates that one entity has a requirement specifying who or what must be the beneficiary of a particular action, service, or resource.
-
C.
supportsAccountType
Indicates that one entity is compatible with, or able to operate for, a specified type or category of account.
-
D.
supportsParticipantType
Indicates that an entity is compatible with, or designed to work with, a specified type or category of participant.
-
E.
beneficiaryChangeAllowed
Indicates that changing or updating the designated beneficiary is permitted under the relevant rules or agreement.
- 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_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. |
Created at: March 6, 2026, 9:58 p.m.