Triple
T22336399
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Plan L |
E552156
|
entity |
| Predicate | premiumsMayVaryBy |
P98150
|
FINISHED |
| Object | insurance company |
—
|
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: insurance company | Statement: [Plan L, premiumsMayVaryBy, insurance company]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: premiumsMayVaryBy Context triple: [Plan L, premiumsMayVaryBy, insurance company]
-
A.
rateVariesBy
chosen
Indicates that the rate of something changes depending on a specified factor, condition, or category.
-
B.
termVariesBy
Indicates that the value or meaning of a term changes depending on a specified factor, such as context, dimension, or condition.
-
C.
creditPolicyVariesBy
Indicates that the terms or rules of a credit policy differ depending on a specified factor, such as customer, product, region, or time period.
-
D.
usageVariesBy
Indicates that the way something is used differs depending on a specified factor, such as context, user, location, or conditions.
-
E.
viewVariesAmong
Indicates that the way something is viewed, perceived, or interpreted differs across multiple entities or contexts.
- 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_69e11e494eec81909c4d2d51f69499d9 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1577f2f208190ac6270ac4581fa15 |
completed | April 29, 2026, 12:57 a.m. |
| PD | Predicate disambiguation | batch_69e7300c20088190a59e5bf9e70384f3 |
completed | April 21, 2026, 8:06 a.m. |
Created at: April 16, 2026, 8:43 p.m.