Triple
T14371450
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | RankBrain |
E356366
|
entity |
| Predicate | partOf |
P40
|
FINISHED |
| Object | Google Search |
E72248
|
NE 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: Google Search | Statement: [RankBrain, partOf, Google Search]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Google Search Context triple: [RankBrain, partOf, Google Search]
-
A.
Google Search
chosen
Google Search is a widely used web search engine developed by Google that allows users to find information, websites, images, and other content across the internet.
-
B.
OpenSearch
OpenSearch is an open-source, community-driven search and analytics engine and suite derived from Elasticsearch, used for full-text search, log analytics, and observability at scale.
-
C.
Internet search
Internet search is the process of using specialized software and algorithms to locate relevant information across the World Wide Web based on user queries.
-
D.
Qwant
Qwant is a French privacy-focused search engine that emphasizes user anonymity and does not track or profile its users.
-
E.
Microsoft Search API
Microsoft Search API is a developer interface that enables unified, intelligent search experiences across Microsoft 365 data and services.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d8279163a081908aec45c0e3f1e02f |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de8fb2082c8190b42cc5f2bab4f574 |
completed | April 14, 2026, 7:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd648135188190af86b1b2be2fe0e0 |
completed | May 8, 2026, 4:20 a.m. |
Created at: April 10, 2026, 1:15 a.m.