Triple

T15132030
Position Surface form Disambiguated ID Type / Status
Subject Google Tag Manager E361443 entity
Predicate supportsPlatform P203 FINISHED
Object AMP
AMP (Accelerated Mobile Pages) is an open-source web component framework designed to create fast-loading, streamlined web pages, especially for mobile devices.
 E1139167 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: AMP | Statement: [Google Tag Manager, supportsPlatform, AMP]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: AMP
Context triple: [Google Tag Manager, supportsPlatform, AMP]
  • A. AMP
    AMP is the abbreviated name for the Air Member for Personnel, a senior Royal Air Force appointment responsible for personnel and manpower matters.
  • B. ARAM
    ARAM is a fast-paced League of Legends game mode where teams fight continuously on a single narrow bridge-like map with randomly assigned champions.
  • C. ADS
    ADS is a widely used digital library and search platform for astronomy and astrophysics research literature maintained by the Smithsonian Astrophysical Observatory and NASA.
  • D. ADS
    ADS is the stock ticker symbol under which the global sportswear company Adidas is traded on the Frankfurt Stock Exchange.
  • E. ADS
    ADS is the three-letter IATA airport code for Addison Airport, a general aviation airport serving the Dallas–Fort Worth area in Texas, United States.
  • 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: AMP
Triple: [Google Tag Manager, supportsPlatform, AMP]
Generated description
AMP (Accelerated Mobile Pages) is an open-source web component framework designed to create fast-loading, streamlined web pages, especially for mobile devices.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: AMP
Target entity description: AMP (Accelerated Mobile Pages) is an open-source web component framework designed to create fast-loading, streamlined web pages, especially for mobile devices.
  • A. AMP
    AMP is the abbreviated name for the Air Member for Personnel, a senior Royal Air Force appointment responsible for personnel and manpower matters.
  • B. ARAM
    ARAM is a fast-paced League of Legends game mode where teams fight continuously on a single narrow bridge-like map with randomly assigned champions.
  • C. ADS
    ADS is a widely used digital library and search platform for astronomy and astrophysics research literature maintained by the Smithsonian Astrophysical Observatory and NASA.
  • D. ADS
    ADS is the stock ticker symbol under which the global sportswear company Adidas is traded on the Frankfurt Stock Exchange.
  • E. ADS
    ADS is the three-letter IATA airport code for Addison Airport, a general aviation airport serving the Dallas–Fort Worth area in Texas, United States.
  • 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_69d85a06450081909c5a14ea9851a15e completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e005b194748190801e3956bf2429d4 completed April 15, 2026, 9:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69feb7fa449c8190aed8941168b063c3 completed May 9, 2026, 4:28 a.m.
NEDg Description generation batch_69febbfb58608190830eca7f9a78fc9c completed May 9, 2026, 4:45 a.m.
NED2 Entity disambiguation (via description) batch_69febc842a7081908a85ba2833212650 completed May 9, 2026, 4:48 a.m.
Created at: April 10, 2026, 3:06 a.m.