Triple
T200056
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Guaranteed Rate |
E4083
|
entity |
| Predicate | hasChannel |
P8080
|
FINISHED |
| Object | retail mortgage lending |
—
|
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: retail mortgage lending | Statement: [Guaranteed Rate, hasChannel, retail mortgage lending]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasChannel Context triple: [Guaranteed Rate, hasChannel, retail mortgage lending]
-
A.
hasSisterChannel
Indicates that one media channel is related to another as its sister channel, typically under common ownership or branding.
-
B.
hasCharacteristic
Indicates that an entity possesses, exhibits, or is defined by a particular attribute, feature, or quality.
-
C.
hasClient
Indicates that an entity maintains a client relationship with another entity, typically as a provider of goods or services.
-
D.
hasLanes
Indicates that an entity, such as a road or pathway, is divided into one or more distinct lanes for traffic or movement.
-
E.
sisterChannel
Indicates that one channel is a sibling or counterpart to another channel, typically under the same ownership or network.
- F. None of above. chosen
Provenance (4 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_69a254bca59881909a15e1496f1508c7 |
completed | Feb. 28, 2026, 2:36 a.m. |
| NER | Named-entity recognition | batch_69a25bcc6dc88190b8c24b485588dfe4 |
completed | Feb. 28, 2026, 3:06 a.m. |
| PD | Predicate disambiguation | batch_69a25b4886b48190b46fd2244648a098 |
completed | Feb. 28, 2026, 3:04 a.m. |
| PDg | Predicate description generation | batch_69a25bc6ba208190aa8bec59d32f95fd |
completed | Feb. 28, 2026, 3:06 a.m. |
Created at: Feb. 28, 2026, 2:44 a.m.