Triple
T28807748
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Comfortline |
E727425
|
entity |
| Predicate | lowerThanTrim |
P122596
|
FINISHED |
| Object | Highline |
—
|
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: Highline | Statement: [Comfortline, lowerThanTrim, Highline]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lowerThanTrim Context triple: [Comfortline, lowerThanTrim, Highline]
-
A.
trimLevelBelow
chosen
Indicates that one entity’s trim level is lower or less equipped than another entity’s trim level.
-
B.
lowerTerminus
Indicates that one entity serves as the lower endpoint or downstream terminus of another entity, such as a route, segment, or connection.
-
C.
lowerLimit
Indicates that one value serves as the minimum or smallest allowable bound or threshold for another value or range.
-
D.
lowerValueIndicates
Indicates that a smaller numerical value of a property or measurement corresponds to a greater degree, better outcome, or stronger presence of the relevant characteristic.
-
E.
lowerLeftTrigram
Indicates that one entity is the trigram located in the lower-left position relative to another entity in a structured arrangement (such as a hexagram).
- 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_69f0319c38948190bca746ad60fd25ba |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69f6645ba71c81908044ade6ab577018 |
completed | May 2, 2026, 8:53 p.m. |
| PD | Predicate disambiguation | batch_69f663362c008190a22afed262f1e426 |
completed | May 2, 2026, 8:48 p.m. |
Created at: April 28, 2026, 6:29 a.m.