Triple
T13959303
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Delta variant |
E335749
|
entity |
| Predicate | whoDesignationDate |
P6938
|
FINISHED |
| Object | May 2021 |
—
|
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: May 2021 | Statement: [Delta variant, whoDesignationDate, May 2021]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: whoDesignationDate Context triple: [Delta variant, whoDesignationDate, May 2021]
-
A.
nominationDate
Indicates the date on which an entity is formally proposed or put forward for a position, award, or role.
-
B.
U.S._presidentWhoDesignated
Indicates that one entity is a U.S. president who officially designated or assigned a particular status, role, or classification to another entity.
-
C.
designationDate
chosen
Indicates the date on which an entity is formally assigned, designated, or given a particular status or role.
-
D.
yearDesignated
Indicates the specific year in which something was formally designated, assigned, or given an official status.
-
E.
appointedBy
Indicates that one entity has been formally selected or assigned to a position, role, or office by another entity.
- 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_69d81c61f3508190aaf2ca0dc0002c59 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2e7b2f908190aa32f22298964746 |
completed | April 14, 2026, 12:09 p.m. |
| PD | Predicate disambiguation | batch_69de05a3ccf88190b45c742db483fa08 |
completed | April 14, 2026, 9:15 a.m. |
Created at: April 9, 2026, 10:17 p.m.