Triple
T4051651
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Google Ad Exchange |
E84598
|
entity |
| Predicate | providesToPublisher |
P53003
|
FINISHED |
| Object | yield optimization |
—
|
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: yield optimization | Statement: [Google Ad Exchange, providesToPublisher, yield optimization]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: providesToPublisher Context triple: [Google Ad Exchange, providesToPublisher, yield optimization]
-
A.
publishesFor
Indicates that one entity issues, releases, or makes content publicly available on behalf of, or in service of, another entity.
-
B.
publishesTo
Indicates that one entity distributes, releases, or makes content available to another entity or destination.
-
C.
hasPublisher
Indicates that an entity is published or issued by a specific publisher.
-
D.
providesThat
Indicates that one entity stipulates, specifies, or sets forth a condition, rule, or provision that applies to another entity or situation.
-
E.
publishesOnTopic
Indicates that an entity (such as a person or organization) produces and releases content whose subject matter concerns a specified topic.
- 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_69aed933bec881909edfa28ebb69c634 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefb8539148190990468c1429be9dd |
completed | March 9, 2026, 4:55 p.m. |
| PD | Predicate disambiguation | batch_69aef90249e4819095e9e043bc4aa9a6 |
completed | March 9, 2026, 4:44 p.m. |
| PDg | Predicate description generation | batch_69aef9fcb31c819098d5287b6fc84f4e |
completed | March 9, 2026, 4:49 p.m. |
Created at: March 9, 2026, 3:37 p.m.