Triple
T17955067
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tolstoy in education |
E448923
|
entity |
| Predicate | researchedIn |
P82862
|
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: [Tolstoy in education, researchedIn, universities]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: researchedIn Context triple: [Tolstoy in education, researchedIn, universities]
-
A.
coResearcher
Indicates that two or more individuals collaborate as peers on the same research work or project.
-
B.
studiedWithin
Indicates that one entity pursued studies or academic work within the scope, context, or boundaries defined by another entity (such as an institution, program, or field).
-
C.
researchedAt
chosen
Indicates that an entity conducted research or scholarly work at a specified institution or location.
-
D.
hasResearched
Indicates that an entity has conducted study, investigation, or systematic inquiry into another entity or topic.
-
E.
researchValue
Indicates that something is considered useful, important, or relevant for research or scholarly investigation.
- 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_69d8b9f8cca8819099836916c56b7c95 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4afaf1ddc8190b480147ac35a4912 |
completed | April 19, 2026, 10:34 a.m. |
| PD | Predicate disambiguation | batch_69e3f8f2bd088190b1e22ad4d9cc8b13 |
completed | April 18, 2026, 9:34 p.m. |
Created at: April 10, 2026, 10:21 a.m.