Triple
T24806186
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hurwitz quaternions |
E620663
|
entity |
| Predicate | hasNormForm |
P151656
|
FINISHED |
| Object | sum of four squares |
—
|
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 of four squares | Statement: [Hurwitz quaternions, hasNormForm, sum of four squares]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNormForm Context triple: [Hurwitz quaternions, hasNormForm, sum of four squares]
-
A.
hasNorm
Indicates that an entity is associated with, governed by, or characterized through a particular norm, rule, or standard.
-
B.
hasNormalFormConcept
chosen
Indicates that something is associated with, or can be represented by, a standardized or canonical conceptual form.
-
C.
normativeFormUntil
Indicates that a particular normative form or standard applies to something only up to a specified point in time, after which it is no longer in effect.
-
D.
hasNonStandardForm
Indicates that an entity possesses a form, variant, or representation that deviates from the standard, canonical, or commonly accepted form.
-
E.
hasNaturalForm
Indicates that an entity possesses an inherent, unaltered, or naturally occurring form or state.
- 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_69e2fabf26bc8190b191faac8f67065b |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f6352fdb788190b9bad30243690743 |
completed | May 2, 2026, 5:32 p.m. |
| PD | Predicate disambiguation | batch_69f63182f1408190bddc1214fcbd6145 |
completed | May 2, 2026, 5:16 p.m. |
Created at: April 18, 2026, 4:50 a.m.