Triple
T16853950
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | IAB Tech Lab |
E409739
|
entity |
| Predicate | developsStandard |
P73
|
FINISHED |
| Object |
Content Taxonomy
Content Taxonomy is a standardized classification framework for digital content used in online advertising to enable consistent categorization, targeting, and reporting across the industry.
|
E1236287
|
NE FINISHED |
How this triple was built (4 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: Content Taxonomy | Statement: [IAB Tech Lab, developsStandard, Content Taxonomy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Content Taxonomy Context triple: [IAB Tech Lab, developsStandard, Content Taxonomy]
-
A.
Content Cup
The Content Cup is a collegiate rowing competition in which the Dartmouth College men’s rowing team participates.
-
B.
Concepts and Categories
Concepts and Categories is a collection of philosophical essays by Isaiah Berlin that explores the nature of human thought, language, and classification in the history of ideas.
-
C.
LexLabs
LexLabs is a research and development subsidiary of LexCorp focused on advancing the corporation’s cutting-edge technologies and innovative projects.
-
D.
CMS
CMS is a major general-purpose particle physics detector at CERN’s Large Hadron Collider, designed to investigate fundamental particles and forces, including the Higgs boson.
-
E.
CMS
CMS (Conversational Monitor System) is an interactive single-user operating system and runtime environment that runs as a virtual machine under IBM's VM/370 mainframe virtualization platform.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Content Taxonomy Triple: [IAB Tech Lab, developsStandard, Content Taxonomy]
Generated description
Content Taxonomy is a standardized classification framework for digital content used in online advertising to enable consistent categorization, targeting, and reporting across the industry.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Content Taxonomy Target entity description: Content Taxonomy is a standardized classification framework for digital content used in online advertising to enable consistent categorization, targeting, and reporting across the industry.
-
A.
Content Cup
The Content Cup is a collegiate rowing competition in which the Dartmouth College men’s rowing team participates.
-
B.
Concepts and Categories
Concepts and Categories is a collection of philosophical essays by Isaiah Berlin that explores the nature of human thought, language, and classification in the history of ideas.
-
C.
LexLabs
LexLabs is a research and development subsidiary of LexCorp focused on advancing the corporation’s cutting-edge technologies and innovative projects.
-
D.
CMS
CMS is a major general-purpose particle physics detector at CERN’s Large Hadron Collider, designed to investigate fundamental particles and forces, including the Higgs boson.
-
E.
CMS
CMS (Conversational Monitor System) is an interactive single-user operating system and runtime environment that runs as a virtual machine under IBM's VM/370 mainframe virtualization platform.
- F. None of above. chosen
Provenance (5 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_69d88395e6c88190b22730f335107c14 |
completed | April 10, 2026, 4:59 a.m. |
| NER | Named-entity recognition | batch_69e3b37bbb80819086d844a313625cad |
completed | April 18, 2026, 4:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00bb216fac81909d401c6b9911d1e0 |
completed | May 10, 2026, 5:06 p.m. |
| NEDg | Description generation | batch_6a00bb9b2b1881908f9f5c3dd1a2d500 |
completed | May 10, 2026, 5:08 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a00bc3a4b888190bd190b9330e2777d |
completed | May 10, 2026, 5:11 p.m. |
Created at: April 10, 2026, 5:24 a.m.