Triple
T11959818
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CMP Media |
E284637
|
entity |
| Predicate | successor |
P78
|
FINISHED |
| Object | UBM Tech |
E284638
|
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: UBM Tech | Statement: [CMP Media, successor, UBM Tech]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: UBM Tech Context triple: [CMP Media, successor, UBM Tech]
-
A.
UBM Tech
chosen
UBM Tech was a business-to-business media and information company focused on the technology industry, known for publishing specialized tech publications and running industry events and conferences.
-
B.
IDG World Expo
IDG World Expo is a trade show and conference organizer known for producing major technology events and exhibitions worldwide.
-
C.
Ziff-Davis Publishing Company
Ziff-Davis Publishing Company is an American media and publishing firm best known for its influential magazines in science fiction, technology, and computing.
-
D.
TechCrunch
TechCrunch is a leading technology news website and media platform known for its coverage of startups, Silicon Valley, and the tech industry.
-
E.
Computerworld
Computerworld is a long-running information technology magazine and online publication focused on news, analysis, and insights for IT professionals and business technology leaders.
- 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_69d6ab2db38c8190b1f0ed6663ef8ada |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d9036941948190b150369094551731 |
completed | April 10, 2026, 2:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f4592fa9a48190a0450e3d0c57c4d3 |
completed | May 1, 2026, 7:41 a.m. |
Created at: April 8, 2026, 9:45 p.m.