Triple
T16806427
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Regal GS |
E408492
|
entity |
| Predicate | trimDifferentiation |
P61682
|
FINISHED |
| Object | more powerful engines than standard Regal |
—
|
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: more powerful engines than standard Regal | Statement: [Regal GS, trimDifferentiation, more powerful engines than standard Regal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: trimDifferentiation Context triple: [Regal GS, trimDifferentiation, more powerful engines than standard Regal]
-
A.
trimCharacteristic
Indicates that one entity defines or specifies a trimming-related property or feature of another entity.
-
B.
distinction
Indicates that one entity is recognized, treated, or classified as different or separate from another.
-
C.
categoryDistinguishedFrom
Indicates that one category is explicitly distinguished from another, clarifying that they are separate and should not be confused.
-
D.
differIn
chosen
Indicates that two entities are not the same in at least one specified aspect, attribute, or value.
-
E.
aimsToDistinguish
Indicates an intention or effort by one entity to set itself or something else apart from others by highlighting differences or unique characteristics.
- 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_69d88393905081908d00a86b99996ac8 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e3b2cd1e8c8190a7a05ba255f711c7 |
completed | April 18, 2026, 4:35 p.m. |
| PD | Predicate disambiguation | batch_69e32b814b188190aee525f8779203cd |
completed | April 18, 2026, 6:58 a.m. |
Created at: April 10, 2026, 5:22 a.m.