Triple
T4051987
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Xandr |
E84604
|
entity |
| Predicate | foundedAs |
P364
|
FINISHED |
| Object | AppNexus |
E84604
|
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: AppNexus | Statement: [Xandr, foundedAs, AppNexus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: AppNexus Context triple: [Xandr, foundedAs, AppNexus]
-
A.
Xandr
chosen
Xandr is a digital advertising and analytics platform that provides tools for programmatic ad buying, selling, and campaign optimization across multiple channels.
-
B.
Magnite
Magnite is a leading independent sell-side advertising platform that helps publishers manage and monetize digital ad inventory across channels like CTV, video, and display.
-
C.
PubMatic
PubMatic is a digital advertising technology company that provides a sell-side platform (SSP) enabling publishers to manage and optimize programmatic ad inventory and revenue.
-
D.
IAB Tech Lab
IAB Tech Lab is a global industry body that develops technical standards and solutions to support and improve digital advertising.
-
E.
Google Ad Manager
Google Ad Manager is Google's unified advertising platform that helps publishers manage, serve, and optimize digital ads across web, app, and video inventory.
- 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_69aed933bec881909edfa28ebb69c634 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefb869c34819097ec3bebe402d37b |
completed | March 9, 2026, 4:55 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5629e75e88190935ae3e7db8eb12f |
completed | March 14, 2026, 1:29 p.m. |
Created at: March 9, 2026, 3:37 p.m.