Triple
T36704331
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Extensions of Recurrent Neural Network Language Model |
E906312
|
entity |
| Predicate | affiliationOfAuthor |
P16016
|
FINISHED |
| Object | Tomas Mikolov |
—
|
NE NERFINISHED |
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: Tomas Mikolov | Statement: [Extensions of Recurrent Neural Network Language Model, affiliationOfAuthor, Tomas Mikolov]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: affiliationOfAuthor Context triple: [Extensions of Recurrent Neural Network Language Model, affiliationOfAuthor, Tomas Mikolov]
-
A.
subjectAffiliation
Indicates that a subject is formally associated or connected with a particular organization, group, or institution.
-
B.
hasAuthorAffiliationAtTimeOfPublication
chosen
Indicates that an author was affiliated with a particular organization or institution at the time a work was published.
-
C.
composerAffiliation
Indicates that a composer is formally associated with, employed by, or otherwise connected to a particular organization, institution, or group.
-
D.
editorAffiliation
Indicates that an editor is affiliated with, or belongs to, a particular organization or institution.
-
E.
compilerAffiliation
Indicates a relationship where a compiler is associated with, belongs to, or is produced/maintained by a particular organization, project, or 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_69f76e7195c48190b5580c9cfb01e95f |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f7c80e09c481909a05f65c9c2cafdf |
completed | May 3, 2026, 10:11 p.m. |
| PD | Predicate disambiguation | batch_69f7c4796ebc819084a0dc08505e5f14 |
completed | May 3, 2026, 9:56 p.m. |
Created at: May 3, 2026, 4:12 p.m.