Triple
T19905122
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Whitepages |
E478392
|
entity |
| Predicate | hasProduct |
P3585
|
FINISHED |
| Object | Whitepages for Business |
—
|
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: Whitepages for Business | Statement: [Whitepages, hasProduct, Whitepages for Business]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Whitepages for Business Context triple: [Whitepages, hasProduct, Whitepages for Business]
-
A.
Whitepages
chosen
Whitepages is a widely used online directory service that provides contact and background information on individuals and businesses.
-
B.
Bluepages
Bluepages is the introductory section of The Bluebook that provides simplified legal citation rules tailored for practitioners, students, and non-academic legal writing.
-
C.
Coremetrics LIVEmail
Coremetrics LIVEmail is an email marketing and analytics solution that integrates with Coremetrics’ web analytics platform to enable targeted, data-driven email campaigns.
-
D.
Audience Builder
Audience Builder is a Marketing Cloud feature that lets users define, segment, and manage audiences based on customer data and behaviors for targeted campaigns.
-
E.
Yellow Pages
Yellow Pages is a traditional printed and online business directory service that organizes companies and services by category for consumer reference.
- 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_69d8e520682081909892916424699bd5 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e65945cc2081908224902d5f042d7a |
completed | April 20, 2026, 4:50 p.m. |
Created at: April 10, 2026, 1:52 p.m.