Triple
T18008676
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HotBot |
E430819
|
entity |
| Predicate | competitor |
P1375
|
FINISHED |
| Object | Yahoo! Search |
—
|
NE NERFINISHED |
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: Yahoo! Search | Statement: [HotBot, competitor, Yahoo! Search]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yahoo! Search Context triple: [HotBot, competitor, Yahoo! Search]
-
A.
Yahoo! Search
chosen
Yahoo! Search is a web search engine developed by Yahoo that was once one of the most popular gateways for finding information on the internet.
-
B.
Yandex Search
Yandex Search is a Russian-developed web search engine that powers Yandex’s ecosystem of online services and tools.
-
C.
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.
-
D.
Ask Jeeves (search engine brand name)
Ask Jeeves was an early web search engine brand best known for its question‑and‑answer style interface featuring a virtual butler character.
-
E.
WSearch
WSearch is the Windows Search background service that indexes files, emails, and other content to enable fast search functionality in the Windows operating system.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b904530081908bf341d842464856 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4b51e13788190bebbbdd7340e0982 |
completed | April 19, 2026, 10:57 a.m. |
Created at: April 10, 2026, 10:24 a.m.