Triple
T6293567
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bernoulli numbers |
E141076
|
entity |
| Predicate | recurrenceRelation |
P46243
|
FINISHED |
| Object | \sum_{k=0}^{n} {n+1 \choose k} B_k = 0 for n \ge 1 |
—
|
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: \sum_{k=0}^{n} {n+1 \choose k} B_k = 0 for n \ge 1 | Statement: [Bernoulli numbers, recurrenceRelation, \sum_{k=0}^{n} {n+1 \choose k} B_k = 0 for n \ge 1]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: recurrenceRelation
Context triple: [Bernoulli numbers, recurrenceRelation, \sum_{k=0}^{n} {n+1 \choose k} B_k = 0 for n \ge 1]
-
A.
recurrence
Indicates that an event, condition, or state happens again or repeatedly over time, often after a period of absence or resolution.
-
B.
recurs
Indicates that an event, condition, or pattern happens again, often repeatedly or at regular intervals, after having occurred before.
-
C.
isLinearRecurrenceOfOrder
chosen
Indicates that one sequence or function is defined by a linear recurrence relation of a specified order, where each term is a linear combination of a fixed number of preceding terms.
-
D.
usesRecursion
Indicates that an entity performs an operation or defines a process by invoking itself, directly or indirectly, as part of its execution.
-
E.
recursIn
Indicates that an event, pattern, or entity appears repeatedly or returns multiple times within a given context, sequence, or timeframe.
- 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_69c008cdf2ac8190bb640c94478fb4ed |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c06438654481908c9833c5f0d61773 |
completed | March 22, 2026, 9:50 p.m. |
| PD | Predicate disambiguation | batch_69c060df0d8881908215575862ef6831 |
completed | March 22, 2026, 9:36 p.m. |
Created at: March 22, 2026, 4:27 p.m.