Triple
T38609378
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bernstein–Gelfand–Gelfand resolution |
E934435
|
entity |
| Predicate | exactAt |
P191287
|
FINISHED |
| Object | all terms except the last |
—
|
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: all terms except the last | Statement: [Bernstein–Gelfand–Gelfand resolution, exactAt, all terms except the last]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: exactAt Context triple: [Bernstein–Gelfand–Gelfand resolution, exactAt, all terms except the last]
-
A.
exactFor
Indicates that one entity corresponds to or matches another entity with complete precision, without any deviation or approximation.
-
B.
timeDefinite
Indicates that the associated event or state occurs at a clearly specified, fixed point or interval in time.
-
C.
constantExactness
Indicates that a value or relationship holds with complete, unvarying precision, without any approximation or deviation.
-
D.
posedAt
Indicates that something (such as a question, challenge, or problem) is directed toward or presented to a particular target or context.
-
E.
morePreciseDate
Indicates that one date value specifies a more detailed or exact point in time than another related date value.
- F. None of above. chosen
Provenance (4 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_69f76eccd6d081909ccce171011739a1 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fcdb0de8c08190928cd1323f80ab5c |
completed | May 7, 2026, 6:33 p.m. |
| PD | Predicate disambiguation | batch_69fcd9017dd88190b32a73fe78909740 |
completed | May 7, 2026, 6:25 p.m. |
| PDg | Predicate description generation | batch_69fcdb0cf6008190b27046b694f84356 |
completed | May 7, 2026, 6:33 p.m. |
Created at: May 3, 2026, 4:32 p.m.