Triple
T3636590
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | IV |
E77082
|
entity |
| Predicate | subtractiveRule |
P38902
|
FINISHED |
| Object | 1 subtracted from 5 equals 4 |
—
|
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: 1 subtracted from 5 equals 4 | Statement: [IV, subtractiveRule, 1 subtracted from 5 equals 4]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: subtractiveRule Context triple: [IV, subtractiveRule, 1 subtracted from 5 equals 4]
-
A.
isSubtractiveCombination
chosen
Indicates that one entity is formed or derived by subtracting one or more components, values, or parts of another entity.
-
B.
compositionRule
Indicates how multiple elements or components are combined or arranged according to a specific rule or pattern.
-
C.
cutRule
Indicates that one entity applies or enforces a rule that removes, prunes, or eliminates certain elements or possibilities from consideration.
-
D.
usesRulesFrom
Indicates that one entity applies, follows, or is governed by the rules defined or provided by another entity.
-
E.
expandedUnderRuleOf
Indicates that an entity grew, spread, or increased in scope during the period when another entity (typically a ruler, regime, or governing authority) was in power.
- 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_69ad85dd0be48190b738990cb20c4731 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc3278bb8819098bbeac023410111 |
completed | March 8, 2026, 6:42 p.m. |
| PD | Predicate disambiguation | batch_69adb842be7c8190b7dfdb7c906f294c |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:24 p.m.