Triple
T27567610
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bartels–Stewart algorithm |
E695944
|
entity |
| Predicate | originalJournal |
P40991
|
FINISHED |
| Object | Communications of the ACM |
—
|
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: Communications of the ACM | Statement: [Bartels–Stewart algorithm, originalJournal, Communications of the ACM]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalJournal Context triple: [Bartels–Stewart algorithm, originalJournal, Communications of the ACM]
-
A.
originalPublicationForm
Indicates the format or medium in which a work was first originally published.
-
B.
originalColumnPublication
Indicates that a publication is the original source in which a particular column or columnar content first appeared.
-
C.
originalManuscriptBy
Indicates that one entity is the original manuscript created or authored by another entity.
-
D.
originalPublicationOfWholeWork
chosen
Indicates that one entity is the original publication in which an entire work was first made publicly available.
-
E.
originallyUnpublished
Indicates that the work or content was not previously published at the time of its original creation or release.
- 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_69ef53891af88190a193c5e2a1dac9b1 |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69fde9fc184c8190bebef35df0e76076 |
completed | May 8, 2026, 1:49 p.m. |
| PD | Predicate disambiguation | batch_69fde6e5beb4819094945a695e961d88 |
completed | May 8, 2026, 1:36 p.m. |
Created at: April 27, 2026, 1:42 p.m.