Triple
T34411299
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Economy Skycouch |
E883273
|
entity |
| Predicate | comfortLevelComparedTo |
P9054
|
FINISHED |
| Object | more comfortable than standard economy seat |
—
|
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 comfortable than standard economy seat | Statement: [Economy Skycouch, comfortLevelComparedTo, more comfortable than standard economy seat]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: comfortLevelComparedTo Context triple: [Economy Skycouch, comfortLevelComparedTo, more comfortable than standard economy seat]
-
A.
comparisonLevel
Indicates the degree or intensity to which two or more entities are being compared within a given context.
-
B.
relativeComfort
chosen
Indicates a comparative relationship where one entity is judged to be more or less comfortable than another under given conditions.
-
C.
comfort
Indicates providing physical or emotional ease, reassurance, or relief from distress to another entity.
-
D.
difficultyRelativeTo
Indicates that one entity’s level of difficulty is being compared to and expressed in relation to another entity’s level of difficulty.
-
E.
confidenceLevel
Indicates the degree of certainty or assurance associated with a particular claim, decision, or outcome.
- 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_69f349c1f2208190a09a489bb8b2719d |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f71947ad88819082ab9d85dd493b01 |
completed | May 3, 2026, 9:45 a.m. |
| PD | Predicate disambiguation | batch_69f71824431081908d9685d2462ea242 |
completed | May 3, 2026, 9:40 a.m. |
Created at: May 1, 2026, 1:59 a.m.