Triple
T36350447
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Central Applications Office |
E895186
|
entity |
| Predicate | applicationDeadlineType |
P200310
|
FINISHED |
| Object | annual fixed deadlines |
—
|
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: annual fixed deadlines | Statement: [Central Applications Office, applicationDeadlineType, annual fixed deadlines]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: applicationDeadlineType Context triple: [Central Applications Office, applicationDeadlineType, annual fixed deadlines]
-
A.
hasDeadline
Indicates that an entity is associated with a specific due date or time by which it must be completed or fulfilled.
-
B.
appliedDate
Indicates the date on which an application or request was submitted or made.
-
C.
secondaryApplicationType
Indicates the specific kind or category of a secondary application associated with an entity or primary application.
-
D.
admissionDate
Indicates the date on which an entity (such as a person, application, or item) is formally admitted, accepted, or entered into a system or institution.
-
E.
UNAdmissionDate
Indicates the date on which an entity was officially admitted as a member of the United Nations.
- 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_69f76e4f437c8190a1af3ea2564f41f5 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69ff7fc835f08190afd1f8129b7a62a2 |
completed | May 9, 2026, 6:41 p.m. |
| PD | Predicate disambiguation | batch_69ff7f2e99ac8190ba372a1358a05a30 |
completed | May 9, 2026, 6:38 p.m. |
| PDg | Predicate description generation | batch_69ff7fc715208190a8e4e2cc5aa72d2c |
completed | May 9, 2026, 6:41 p.m. |
Created at: May 3, 2026, 4:09 p.m.