Triple
T10087563
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Evolution and the Genetics of Populations |
E215258
|
entity |
| Predicate | theoryDiscussed |
P75843
|
FINISHED |
| Object | shifting balance theory |
—
|
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: shifting balance theory | Statement: [Evolution and the Genetics of Populations, theoryDiscussed, shifting balance theory]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: theoryDiscussed Context triple: [Evolution and the Genetics of Populations, theoryDiscussed, shifting balance theory]
-
A.
discussed
Indicates that one entity talked about, examined, or debated a topic, issue, or other entity with someone else.
-
B.
theoryType
Indicates the classification relationship that specifies what type or category of theory an entity belongs to.
-
C.
theorized
Indicates that one entity has proposed or developed a theoretical explanation or hypothesis about another entity or phenomenon.
-
D.
discourse
Indicates that one entity engages in extended verbal or written communication or discussion with another entity.
-
E.
discussedAs
chosen
Indicates that one entity is talked about, treated, or examined in terms of another entity, often as an example, case, or framing concept.
- 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_69ca83a1eed081908b2e9580f2ebeea7 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cdd04875748190a81d1e9ad68dda96 |
completed | April 2, 2026, 2:11 a.m. |
| PD | Predicate disambiguation | batch_69cd4b97870481908f7a89df10d58a9e |
completed | April 1, 2026, 4:45 p.m. |
Created at: March 30, 2026, 9:01 p.m.