Triple
T14008690
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Omicron variant |
E337019
|
entity |
| Predicate | hasKeyMutationLocation |
P18908
|
FINISHED |
| Object | spike protein |
—
|
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: spike protein | Statement: [Omicron variant, hasKeyMutationLocation, spike protein]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasKeyMutationLocation Context triple: [Omicron variant, hasKeyMutationLocation, spike protein]
-
A.
hasKeyLocation
chosen
Indicates that an entity possesses or is associated with a specific primary or important location relevant to it.
-
B.
hasKeyChange
Indicates that an entity undergoes or involves a change of key, such as a modulation or shift in tonal center.
-
C.
hasKeyChanges
Indicates that one entity undergoes or contains changes in musical key relative to another entity or version.
-
D.
hasKeyPoint
Indicates that one entity includes, contains, or is associated with a specific key point or main idea represented by another entity.
-
E.
hasKeyPhase
Indicates that an entity possesses or is associated with a specific key phase within a process, lifecycle, or sequence.
- 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_69d81c645c5c8190b1fd16a285a1b78a |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2ed44f90819099ad08c09c066b56 |
completed | April 14, 2026, 12:11 p.m. |
| PD | Predicate disambiguation | batch_69dd465dfbc4819090d8c61fd572d35f |
completed | April 13, 2026, 7:39 p.m. |
Created at: April 9, 2026, 10:19 p.m.